https://www.agentclash.dev https://www.agentclash.dev/og?title=AgentClash%3A+AI+Agent+Evaluation+with+Replay+Evidence&subtitle=Run+AI+agents+on+repeatable+real+tasks%2C+compare+trajectories%2C+inspect+replay+evidence%2C+and+turn+failures+into+regression+gates.&kind=marketing 2026-08-14T00:00:00.000Z weekly 1 https://www.agentclash.dev/why https://www.agentclash.dev/og?title=Why+AgentClash&subtitle=Agent+evaluation+should+test+what+an+agent+does+across+a+complete+trajectory%2C+not+only+what+one+model+call+says.&kind=marketing 2026-08-14T00:00:00.000Z monthly 0.7 https://www.agentclash.dev/team https://www.agentclash.dev/og?title=AgentClash+Team&subtitle=Meet+the+team+building+open-source+infrastructure+for+repeatable+AI+agent+evaluation.&kind=marketing 2026-08-14T00:00:00.000Z monthly 0.5 https://www.agentclash.dev/enterprise https://www.agentclash.dev/og?title=Enterprise+AI+Agent+Evaluation&subtitle=Governed+agent+release+gates%2C+private+evaluation+infrastructure%2C+audit+evidence%2C+and+rollout+support+for+platform+teams.&kind=marketing 2026-08-14T00:00:00.000Z monthly 0.82 https://www.agentclash.dev/services https://www.agentclash.dev/og?title=Agent+Evaluation+Services&subtitle=Fixed-scope+services+for+challenge-pack+design%2C+regression+setup%2C+evaluation+pilots%2C+and+platform+adoption.&kind=marketing 2026-08-14T00:00:00.000Z monthly 0.78 https://www.agentclash.dev/resources/eval-checklist https://www.agentclash.dev/og?title=Enterprise+AI+Agent+Evaluation+Checklist&subtitle=A+practical+checklist+for+evaluation+design%2C+release+gates%2C+pilot+evidence%2C+and+procurement+review.&kind=marketing 2026-08-14T00:00:00.000Z monthly 0.77 https://www.agentclash.dev/platform/agent-evaluation https://www.agentclash.dev/og?title=AI+Agent+Evaluation+Platform&subtitle=Evaluate+tool-using+AI+agents+on+real+tasks+with+isolated+sandboxes%2C+scorecards%2C+replay+evidence%2C+and+CI+regression+gates.&kind=marketing 2026-08-14T00:00:00.000Z monthly 0.85 https://www.agentclash.dev/platform/agent-regression-testing https://www.agentclash.dev/og?title=AI+Agent+Regression+Testing&subtitle=Compare+baselines+and+candidates+against+pinned+agent+failures+and+datasets+with+replay+evidence%2C+release+thresholds%2C+and+CI+release+gates.&kind=marketing 2026-08-14T00:00:00.000Z monthly 0.82 https://www.agentclash.dev/platform/datasmith https://www.agentclash.dev/og?title=DataSmith+Synthetic+Agent+Data&subtitle=Generate+diverse+agent+evaluation+datasets+with+weak-versus-strong+Agentic+Self-Instruct+workflows.&kind=marketing 2026-08-14T00:00:00.000Z monthly 0.84 https://www.agentclash.dev/use-cases https://www.agentclash.dev/og?title=Agent+Evaluation+Use+Cases&subtitle=Evaluation+patterns+for+coding%2C+research%2C+and+customer-support+agents.&kind=marketing 2026-08-14T00:00:00.000Z monthly 0.78 https://www.agentclash.dev/features https://www.agentclash.dev/og?title=AgentClash+Features&subtitle=Challenge+packs%2C+scorecards%2C+replay%2C+datasets%2C+regression+suites%2C+and+CI+release+gates.&kind=marketing 2026-08-14T00:00:00.000Z monthly 0.78 https://www.agentclash.dev/industries https://www.agentclash.dev/og?title=AI+Agent+Evaluation+by+Industry&subtitle=Evaluation+guidance+for+regulated+and+evidence-sensitive+industries.&kind=marketing 2026-08-14T00:00:00.000Z monthly 0.78 https://www.agentclash.dev/glossary https://www.agentclash.dev/og?title=Agent+Evaluation+Glossary&subtitle=Definitions+for+agent+evaluation%2C+challenge+packs%2C+release+gates%2C+replay+evidence%2C+and+synthetic+data.&kind=marketing 2026-08-14T00:00:00.000Z monthly 0.78 https://www.agentclash.dev/blog https://www.agentclash.dev/og?title=AgentClash+Blog&subtitle=Engineering+guides%2C+benchmark+analysis%2C+product+updates%2C+and+practical+AI+agent+evaluation+advice.&kind=marketing 2026-08-14T00:00:00.000Z weekly 0.8 https://www.agentclash.dev/benchmarks https://www.agentclash.dev/og?title=AI+Agent+Benchmarks&subtitle=Measured+same-task+agent+comparisons+with+frozen+challenge+packs%2C+scorecards%2C+and+replay+evidence.&kind=marketing 2026-08-14T00:00:00.000Z weekly 0.8 https://www.agentclash.dev/publications https://www.agentclash.dev/og?title=Published+Agent+Evaluation+Artifacts&subtitle=Browse+explicitly+published%2C+redacted+challenge+packs%2C+scorecards%2C+replays%2C+and+agent+tryouts.&kind=publication 2026-08-14T00:00:00.000Z weekly 0.72 https://www.agentclash.dev/try https://www.agentclash.dev/og?title=Try+AgentClash&subtitle=Browse+public+agent+demos+and+start+an+isolated+terminal+only+when+you+explicitly+choose+a+demo.&kind=interactive 2026-08-14T00:00:00.000Z weekly 0.88 https://www.agentclash.dev/tryouts https://www.agentclash.dev/og?title=AI+Agent+Tryouts&subtitle=Run+public+task-gated+agent+tryouts+with+visible+tools%2C+inputs%2C+completed+output%2C+and+trace+export.&kind=interactive 2026-08-14T00:00:00.000Z weekly 0.9 https://www.agentclash.dev/agent-opportunity https://www.agentclash.dev/og?title=AI+Agent+Opportunity+Report&subtitle=Assess+a+company+workflow+for+agent+automation+opportunities%2C+evaluation+needs%2C+and+build-versus-buy+tradeoffs.&kind=interactive 2026-08-14T00:00:00.000Z weekly 0.91 https://www.agentclash.dev/try/biome https://www.agentclash.dev/og?title=Try+Biome+in+browser&subtitle=Fast+formatter+%26+linter+for+JS%2FTS&kind=interactive 2026-08-14T00:00:00.000Z monthly 0.72 https://www.agentclash.dev/try/bun https://www.agentclash.dev/og?title=Try+Bun+in+browser&subtitle=Ultra-fast+JavaScript+runtime+%26+toolkit&kind=interactive 2026-08-14T00:00:00.000Z monthly 0.72 https://www.agentclash.dev/try/claude-code https://www.agentclash.dev/og?title=Try+Claude+Code+in+browser&subtitle=Anthropic%27s+agentic+coding+CLI&kind=interactive 2026-08-14T00:00:00.000Z monthly 0.72 https://www.agentclash.dev/try/codex https://www.agentclash.dev/og?title=Try+Codex+CLI+in+browser&subtitle=OpenAI%27s+coding+agent+in+your+terminal&kind=interactive 2026-08-14T00:00:00.000Z monthly 0.72 https://www.agentclash.dev/try/grok https://www.agentclash.dev/og?title=Try+Grok+CLI+in+browser&subtitle=xAI%27s+Grok%2C+agentic+in+your+terminal&kind=interactive 2026-08-14T00:00:00.000Z monthly 0.72 https://www.agentclash.dev/try/kimi-k2 https://www.agentclash.dev/og?title=Try+Kimi+K2+in+browser&subtitle=Moonshot%27s+agentic+coding+model&kind=interactive 2026-08-14T00:00:00.000Z monthly 0.72 https://www.agentclash.dev/try/opencode https://www.agentclash.dev/og?title=Try+OpenCode+in+browser&subtitle=Open-source+AI+coding+agent+by+SST&kind=interactive 2026-08-14T00:00:00.000Z monthly 0.72 https://www.agentclash.dev/try/qwen3-coder https://www.agentclash.dev/og?title=Try+Qwen3+Coder+in+browser&subtitle=Alibaba%27s+coding-tuned+agent&kind=interactive 2026-08-14T00:00:00.000Z monthly 0.72 https://www.agentclash.dev/try/ripgrep https://www.agentclash.dev/og?title=Try+ripgrep+in+browser&subtitle=Recursively+search+code+with+regex%2C+fast&kind=interactive 2026-08-14T00:00:00.000Z monthly 0.72 https://www.agentclash.dev/try/ruff https://www.agentclash.dev/og?title=Try+Ruff+in+browser&subtitle=Extremely+fast+Python+linter+%26+formatter&kind=interactive 2026-08-14T00:00:00.000Z monthly 0.72 https://www.agentclash.dev/try/uv https://www.agentclash.dev/og?title=Try+uv+in+browser&subtitle=Blazing-fast+Python+package+manager&kind=interactive 2026-08-14T00:00:00.000Z monthly 0.72 https://www.agentclash.dev/pricing https://www.agentclash.dev/og?title=AgentClash+Pricing&subtitle=Free+hosted+and+self-hosted+options%2C+plus+Pro%2C+Team%2C+and+Enterprise+plans+with+bring-your-own+LLM+keys.&kind=marketing 2026-08-14T00:00:00.000Z monthly 0.8 https://www.agentclash.dev/open-source-ai-agent-evaluation https://www.agentclash.dev/og?title=Open+source+AI+agent+evaluation&subtitle=MIT-licensed%2C+self-hostable+AI+agent+evaluation+with+replay%2C+scorecards%2C+and+CI+gates.&kind=seo 2026-08-14T00:00:00.000Z monthly 0.8 https://www.agentclash.dev/agent-evals https://www.agentclash.dev/og?title=Agent+evals&subtitle=Real-task+agent+evals+with+replay+evidence%2C+scorecards%2C+and+CI+regression+gates.&kind=seo 2026-08-14T00:00:00.000Z monthly 0.8 https://www.agentclash.dev/llm-agent-evaluation https://www.agentclash.dev/og?title=LLM+agent+evaluation&subtitle=Evaluate+tool-using+LLM+agents+on+real+tasks+with+replay+and+scorecards.&kind=seo 2026-08-14T00:00:00.000Z monthly 0.8 https://www.agentclash.dev/agent-evaluation-framework https://www.agentclash.dev/og?title=Agent+evaluation+framework&subtitle=Framework+for+real-task+agent+evaluation+with+replay%2C+scorecards%2C+and+CI+gates.&kind=seo 2026-08-14T00:00:00.000Z monthly 0.72 https://www.agentclash.dev/ai-agent-testing https://www.agentclash.dev/og?title=AI+agent+testing&subtitle=Test+AI+agents+on+real+tasks+with+replay+evidence+and+CI+regression+gates.&kind=seo 2026-08-14T00:00:00.000Z monthly 0.72 https://www.agentclash.dev/agent-trajectory-evaluation https://www.agentclash.dev/og?title=Agent+trajectory+evaluation&subtitle=Score+full+agent+trajectories+with+replay+evidence+and+release+gates.&kind=seo 2026-08-14T00:00:00.000Z monthly 0.72 https://www.agentclash.dev/ci-cd-agent-evaluation https://www.agentclash.dev/og?title=CI%2FCD+agent+evaluation&subtitle=Run+agent+evaluation+in+CI%2FCD+with+scorecard+gates+and+replay+evidence.&kind=seo 2026-08-14T00:00:00.000Z monthly 0.72 https://www.agentclash.dev/ai-agent-benchmark https://www.agentclash.dev/og?title=AI+agent+benchmark&subtitle=Benchmark+AI+agents+on+real+tasks+with+replay+and+scorecards.&kind=seo 2026-08-14T00:00:00.000Z monthly 0.72 https://www.agentclash.dev/agent-reliability-benchmark https://www.agentclash.dev/og?title=Agent+reliability+benchmark&subtitle=Benchmark+agent+reliability+on+real+tasks+with+regression+gates.&kind=seo 2026-08-14T00:00:00.000Z monthly 0.72 https://www.agentclash.dev/use-cases/coding-agent-evaluation https://www.agentclash.dev/og?title=Coding+agent+evaluation&subtitle=Evaluate+coding+agents+on+real+repositories+with+replay+and+CI+gates.&kind=seo 2026-08-14T00:00:00.000Z monthly 0.64 https://www.agentclash.dev/use-cases/research-agent-evaluation https://www.agentclash.dev/og?title=Research+agent+evaluation&subtitle=Evaluate+research+agents+on+investigation+tasks+with+replay+and+scorecards.&kind=seo 2026-08-14T00:00:00.000Z monthly 0.64 https://www.agentclash.dev/use-cases/support-agent-evaluation https://www.agentclash.dev/og?title=Support+agent+evaluation&subtitle=Evaluate+support+agents+on+resolution+workflows+with+replay+and+gates.&kind=seo 2026-08-14T00:00:00.000Z monthly 0.64 https://www.agentclash.dev/industries/banking https://www.agentclash.dev/og?title=Banking+agent+evaluation&subtitle=Evaluate+financial+services+agents+with+replay+evidence+and+release+gates.&kind=seo 2026-08-14T00:00:00.000Z monthly 0.64 https://www.agentclash.dev/industries/insurance https://www.agentclash.dev/og?title=Insurance+agent+evaluation&subtitle=Evaluate+insurance+support+agents+with+policy+checks+and+replay.&kind=seo 2026-08-14T00:00:00.000Z monthly 0.64 https://www.agentclash.dev/industries/government https://www.agentclash.dev/og?title=Government+agent+evaluation&subtitle=Evaluate+public-sector+agents+with+replay+and+evidence+bundles.&kind=seo 2026-08-14T00:00:00.000Z monthly 0.64 https://www.agentclash.dev/glossary/agent-evaluation https://www.agentclash.dev/og?title=Agent+evaluation+%28glossary%29&subtitle=Definition+of+agent+evaluation+vs+prompt+testing.&kind=seo 2026-08-14T00:00:00.000Z monthly 0.64 https://www.agentclash.dev/glossary/challenge-pack https://www.agentclash.dev/og?title=Challenge+pack+%28glossary%29&subtitle=Definition+of+AgentClash+challenge+packs.&kind=seo 2026-08-14T00:00:00.000Z monthly 0.64 https://www.agentclash.dev/glossary/release-gate https://www.agentclash.dev/og?title=Release+gate+%28glossary%29&subtitle=Definition+of+agent+release+gates+and+CI+regression+checks.&kind=seo 2026-08-14T00:00:00.000Z monthly 0.64 https://www.agentclash.dev/features/agent-scorecards https://www.agentclash.dev/og?title=Agent+scorecards&subtitle=Scorecards+for+correctness%2C+cost%2C+latency%2C+and+evidence+quality.&kind=seo 2026-08-14T00:00:00.000Z monthly 0.64 https://www.agentclash.dev/features/agent-replay https://www.agentclash.dev/og?title=Agent+replay&subtitle=Replay+tool+calls%2C+artifacts%2C+and+evidence+for+agent+debugging.&kind=seo 2026-08-14T00:00:00.000Z monthly 0.64 https://www.agentclash.dev/features/challenge-packs https://www.agentclash.dev/og?title=Challenge+packs&subtitle=Repeatable+agent+evaluation+workloads+with+scoring+and+CI+gates.&kind=seo 2026-08-14T00:00:00.000Z monthly 0.64 https://www.agentclash.dev/synthetic-data-generation-agents https://www.agentclash.dev/og?title=Synthetic+data+generation+for+agents&subtitle=Weak-vs-strong+synthetic+dataset+generation+for+agent+fine-tuning+and+eval.&kind=seo 2026-08-14T00:00:00.000Z monthly 0.72 https://www.agentclash.dev/agentic-self-instruct https://www.agentclash.dev/og?title=Agentic+Self-Instruct&subtitle=Weak-vs-strong+synthetic+data+loop+inspired+by+Meta+FAIR+Autodata.&kind=seo 2026-08-14T00:00:00.000Z monthly 0.72 https://www.agentclash.dev/trace-to-dataset https://www.agentclash.dev/og?title=Trace+to+dataset&subtitle=Convert+agent+traces+into+synthetic+dataset+seeds+and+eval+coverage.&kind=seo 2026-08-14T00:00:00.000Z monthly 0.64 https://www.agentclash.dev/features/synthetic-dataset-generation https://www.agentclash.dev/og?title=Synthetic+dataset+generation&subtitle=Hosted+weak-vs-strong+generation+for+eval-ready+datasets.&kind=seo 2026-08-14T00:00:00.000Z monthly 0.64 https://www.agentclash.dev/glossary/agentic-self-instruct https://www.agentclash.dev/og?title=Agentic+Self-Instruct+%28glossary%29&subtitle=Definition+of+the+weak-vs-strong+synthetic+data+loop.&kind=seo 2026-08-14T00:00:00.000Z monthly 0.64 https://www.agentclash.dev/compare https://www.agentclash.dev/og?title=AgentClash+vs+prompt-evaluation+tools&subtitle=Compare+AgentClash+with+prompt+evaluation%2C+observability%2C+and+agent+evaluation+tools.&kind=comparison 2026-08-14T00:00:00.000Z monthly 0.8 https://www.agentclash.dev/compare/agentclash-vs-braintrust https://www.agentclash.dev/og?title=AgentClash+vs+Braintrust&subtitle=Compare+AgentClash+end-to-end+agent+evaluation+with+Braintrust%2C+a+prompt+eval+tool.&kind=comparison 2026-08-14T00:00:00.000Z monthly 0.75 https://www.agentclash.dev/compare/agentclash-vs-langsmith https://www.agentclash.dev/og?title=AgentClash+vs+LangSmith&subtitle=Compare+AgentClash+end-to-end+agent+evaluation+with+LangSmith%2C+a+prompt+eval+tool.&kind=comparison 2026-08-14T00:00:00.000Z monthly 0.75 https://www.agentclash.dev/compare/agentclash-vs-promptfoo https://www.agentclash.dev/og?title=AgentClash+vs+Promptfoo&subtitle=Compare+AgentClash+end-to-end+agent+evaluation+with+Promptfoo%2C+a+prompt+eval+tool.&kind=comparison 2026-08-14T00:00:00.000Z monthly 0.75 https://www.agentclash.dev/compare/agentclash-vs-langfuse https://www.agentclash.dev/og?title=AgentClash+vs+Langfuse&subtitle=Compare+AgentClash+end-to-end+agent+evaluation+with+Langfuse%2C+a+prompt+eval+tool.&kind=comparison 2026-08-14T00:00:00.000Z monthly 0.75 https://www.agentclash.dev/compare/agentclash-vs-arize-phoenix https://www.agentclash.dev/og?title=AgentClash+vs+Arize+Phoenix&subtitle=Compare+AgentClash+end-to-end+agent+evaluation+with+Arize+Phoenix%2C+a+prompt+eval+tool.&kind=comparison 2026-08-14T00:00:00.000Z monthly 0.75 https://www.agentclash.dev/compare/agentclash-vs-openai-evals https://www.agentclash.dev/og?title=AgentClash+vs+OpenAI+Evals&subtitle=Compare+AgentClash+end-to-end+agent+evaluation+with+OpenAI+Evals%2C+a+prompt+eval+tool.&kind=comparison 2026-08-14T00:00:00.000Z monthly 0.75 https://www.agentclash.dev/compare/agentclash-vs-deepeval https://www.agentclash.dev/og?title=AgentClash+vs+DeepEval&subtitle=Compare+AgentClash+end-to-end+agent+evaluation+with+DeepEval%2C+a+LLM+eval+framework+tool.&kind=comparison 2026-08-14T00:00:00.000Z monthly 0.75 https://www.agentclash.dev/compare/agentclash-vs-galileo https://www.agentclash.dev/og?title=AgentClash+vs+Galileo&subtitle=Compare+AgentClash+end-to-end+agent+evaluation+with+Galileo%2C+a+LLM+observability+tool.&kind=comparison 2026-08-14T00:00:00.000Z monthly 0.75 https://www.agentclash.dev/compare/agentclash-vs-patronus-ai https://www.agentclash.dev/og?title=AgentClash+vs+Patronus+AI&subtitle=Compare+AgentClash+end-to-end+agent+evaluation+with+Patronus+AI%2C+a+eval+%26+guardrails+tool.&kind=comparison 2026-08-14T00:00:00.000Z monthly 0.75 https://www.agentclash.dev/compare/agentclash-vs-ragas https://www.agentclash.dev/og?title=AgentClash+vs+Ragas&subtitle=Compare+AgentClash+end-to-end+agent+evaluation+with+Ragas%2C+a+RAG+%26+agent+eval+tool.&kind=comparison 2026-08-14T00:00:00.000Z monthly 0.75 https://www.agentclash.dev/compare/agentclash-vs-maxim-ai https://www.agentclash.dev/og?title=AgentClash+vs+Maxim+AI&subtitle=Compare+AgentClash+end-to-end+agent+evaluation+with+Maxim+AI%2C+a+agent+simulation+%26+observability+tool.&kind=comparison 2026-08-14T00:00:00.000Z monthly 0.75 https://www.agentclash.dev/compare/agentclash-vs-mlflow https://www.agentclash.dev/og?title=AgentClash+vs+MLflow&subtitle=Compare+AgentClash+end-to-end+agent+evaluation+with+MLflow%2C+a+MLOps+%26+agent+eval+tool.&kind=comparison 2026-08-14T00:00:00.000Z monthly 0.75 https://www.agentclash.dev/changelog https://www.agentclash.dev/og?title=AgentClash+Changelog&subtitle=Product+updates%2C+improvements%2C+fixes%2C+and+security+changes.&kind=changelog 2026-08-15T00:00:00.000Z weekly 0.75 https://www.agentclash.dev/changelog/2026-08-07 https://www.agentclash.dev/og?title=Fleet%3A+eval+sets+at+cloud+scale%2C+plus+two+new+ways+to+author+a+pack&subtitle=The+Fleet+epic+landed+in+fifteen+pull+requests+%E2%80%94+case-level+fan-out%2C+Kubernetes+sandboxes%2C+per-account+LLM+throttling%2C+eval-set+manifests%2C+a+live+matrix+dashboard%2C+post-hoc+scanners%2C+budgets+with+emergency+stop%2C+OTel+metrics%2C+and+a+Helm+chart.+Alongside+it%3A+one-command+local+setup+for+contributors%2C+custom+OpenAI-compatible+endpoints%2C+pack+drafts+generated+from+a+tryout+or+a+plain-English+description%2C+and+a+machine-readable+public+site.&kind=changelog 2026-08-15T00:00:00.000Z monthly 0.65 https://www.agentclash.dev/changelog/2026-07-02 https://www.agentclash.dev/og?title=A+shared+runtime+module%2C+local+Docker+execution%2C+and+a+big+cleanup&subtitle=Agent+execution+moved+out+of+the+backend+into+a+standalone+%60runtime%60+module+that+the+API+server%2C+worker%2C+and+CLI+all+import+%E2%80%94+the+foundation+for+running+evals+locally.+Local+runs+gained+a+Docker+sandbox+provider+and+bring-your-own-key+credential+resolution.+A+34k-line+removal+pass+retired+dead+and+demoted+surfaces%2C+and+CLI+2.0.0+shipped.&kind=changelog 2026-07-12T00:00:00.000Z monthly 0.65 https://www.agentclash.dev/changelog/2026-06-22 https://www.agentclash.dev/og?title=DataSmith+launch%3A+weak-vs-strong+synthetic+data+for+agents&subtitle=DataSmith+ships+as+an+open-source+Python+SDK+for+high-signal+synthetic+dataset+generation+with+web-grounded+seed+construction%2C+OTLP+trace+ingestion%2C+and+SFT%2FDPO+export.+AgentClash+adds+platform+marketing%2C+docs%2C+and+SEO+surfaces+for+the+hosted+Agentic+Self-Instruct+loop.&kind=changelog 2026-07-01T00:00:00.000Z monthly 0.65 https://www.agentclash.dev/changelog/2026-06-02 https://www.agentclash.dev/og?title=Portable+agent+skills+and+one-command+host+install&subtitle=Twenty-five+portable+Agent+Skills+shipped+with+docs%2C+an+embedded+CLI+snapshot%2C+and+a+standalone+agent-skills+bundle+repo.+Install+or+doctor+skills+on+Claude%2C+Codex%2C+Cursor%2C+OpenClaw%2C+Hermes%2C+and+OpenCode+with+one+command%2C+or+export+an+offline+bundle+as+a+directory+or+tar.gz.&kind=changelog 2026-06-11T00:00:00.000Z monthly 0.65 https://www.agentclash.dev/changelog/2026-05-25 https://www.agentclash.dev/og?title=Datasets%2C+%2Ftry+demos%2C+multi-turn+transcripts%2C+and+Hermes+harness&subtitle=The+datasets+platform+shipped+end-to-end+%E2%80%94+import%2C+generation%2C+trace+ingest%2C+eval+gates%2C+and+full+workspace+UI.+%2Ftry+CLI+demos%2C+multi-turn+transcript+exports%2C+Hermes+harness+support%2C+and+PostHog+analytics+rounded+out+the+release+window.&kind=changelog 2026-06-01T00:00:00.000Z monthly 0.65 https://www.agentclash.dev/changelog/2026-05-15 https://www.agentclash.dev/og?title=Security+packs%2C+multi-turn+eval%2C+and+replay+polish&subtitle=Security-family+challenge+packs%2C+stress-run+CLI%2C+and+vault+boundary+harnesses+established+AgentClash+as+a+security+eval+surface.+Multi-turn+evaluation+with+human+takeover+and+case+templating+extended+the+engine+beyond+single-shot+runs.&kind=changelog 2026-05-24T00:00:00.000Z monthly 0.65 https://www.agentclash.dev/changelog/2026-05-05 https://www.agentclash.dev/og?title=CI+intelligence%2C+prompt+eval%2C+and+GitHub-native+workflows&subtitle=Failure+clusters%2C+regression+provenance%2C+and+CI+setup+generators+connected+the+eval+loop+to+GitHub.+Prompt+eval+CLI+commands%2C+the+PR+comment+bot%2C+and+E2B+harness+runners+closed+the+gap+between+local+runs+and+production+gates.&kind=changelog 2026-05-14T00:00:00.000Z monthly 0.65 https://www.agentclash.dev/changelog/2026-04-25 https://www.agentclash.dev/og?title=Peer+standings%2C+CLI+distribution%2C+and+a+redesigned+public+site&subtitle=Live+peer+standings+injected+into+running+agents%2C+the+CLI+shipped+through+npm+with+production+defaults%2C+and+the+marketing+site+got+a+full+redesign+%E2%80%94+%2Fwhy%2C+pricing%2C+docs+foundation%2C+and+broadcast-style+run+views.&kind=changelog 2026-05-04T00:00:00.000Z monthly 0.65 https://www.agentclash.dev/changelog/2026-04-15 https://www.agentclash.dev/og?title=Scoring+depth%2C+failure+review%2C+and+the+first+regression+suite+UI&subtitle=The+evaluation+engine+gained+deterministic+validators%2C+LLM+judge+dimensions%2C+and+behavioral+scoring.+Failure+review+and+regression+suites+landed+in+the+workspace+UI%2C+alongside+CLI+distribution+hardening+and+the+xAI+provider+adapter.&kind=changelog 2026-04-24T00:00:00.000Z monthly 0.65 https://www.agentclash.dev/blog/top-ai-agent-evaluation-tools-2026 https://www.agentclash.dev/og?title=Top+AI+Agent+Evaluation+Tools+in+2026%3A+Prompt+Evals+vs+Real-Task+Gates&subtitle=A+practical+2026+buyer+guide+to+AI+agent+evaluation+tools.+Compare+LangSmith%2C+Braintrust%2C+Maxim%2C+MLflow%2C+DeepEval%2C+and+open-source+sandboxed+agent+evals+with+CI+release+gates.&kind=blog 2026-07-09T00:00:00.000Z monthly 0.7 https://www.agentclash.dev/blog/introducing-datasmith-synthetic-agent-data https://www.agentclash.dev/og?title=Introducing+DataSmith%3A+High-Signal+Synthetic+Data+for+AI+Agents&subtitle=DataSmith+is+an+open-source+Python+SDK+for+weak-vs-strong+synthetic+dataset+generation.+Use+it+locally+for+SFT+and+DPO+export%2C+or+inside+AgentClash+for+eval-ready+datasets+and+regression+tests.&kind=blog 2026-07-01T00:00:00.000Z monthly 0.7 https://www.agentclash.dev/blog/evaluating-bilingual-customer-support-agents https://www.agentclash.dev/og?title=Evaluating+Bilingual+Customer+Support+Agents%3A+Arabic%2C+English%2C+and+Release+Evidence&subtitle=Bilingual+support+agents+need+evals+on+real+ticket+flows+in+each+language%2C+not+a+single+translated+prompt.+How+to+build+Arabic+and+English+cases+with+replay+and+gates.&kind=blog 2026-06-15T00:00:00.000Z monthly 0.7 https://www.agentclash.dev/blog/ai-agent-governance-middle-east-enterprises https://www.agentclash.dev/og?title=AI+Agent+Governance+for+Middle+East+Enterprises%3A+Residency%2C+Evidence%2C+and+Release+Gates&subtitle=UAE+and+GCC+buyers+need+clear+separation+between+data+residency%2C+sovereign+cloud%2C+and+agent+release+evidence.+A+governance+checklist+grounded+in+repeatable+eval+workflows.&kind=blog 2026-06-14T00:00:00.000Z monthly 0.7 https://www.agentclash.dev/blog/building-agent-eval-program-regulated-enterprise https://www.agentclash.dev/og?title=Building+an+Agent+Eval+Program+in+a+Regulated+Enterprise&subtitle=Regulated+enterprises+need+versioned+workloads%2C+audit-friendly+replay%2C+baseline+gates%2C+and+CI+handoff.+A+phased+plan+to+stand+up+a+governed+agent+eval+program.&kind=blog 2026-06-13T00:00:00.000Z monthly 0.7 https://www.agentclash.dev/blog/when-the-us-government-banned-fable-5 https://www.agentclash.dev/og?title=When+the+US+Government+Banned+Fable+5&subtitle=Three+days+after+launch%2C+the+US+Commerce+Department+ordered+Anthropic+to+pull+its+best+model.+A+model%27s+availability+is+now+a+jurisdictional+variable%2C+and+that+changes+how+everyone+should+build.&kind=blog 2026-06-13T00:00:00.000Z monthly 0.7 https://www.agentclash.dev/blog/why-ai-pilot-failed-agent-eval-second-attempt https://www.agentclash.dev/og?title=Why+Your+AI+Pilot+Failed+%28and+How+Eval+Fixes+the+Second+Attempt%29&subtitle=Most+AI+agent+pilots+fail+on+workload+mismatch%2C+missing+baselines%2C+and+unreviewable+evidence.+How+to+redesign+the+second+attempt+with+governed+benchmarks+and+replay.&kind=blog 2026-06-12T00:00:00.000Z monthly 0.7 https://www.agentclash.dev/blog/agent-evaluation-vs-prompt-evaluation-braintrust https://www.agentclash.dev/og?title=Agent+Evaluation+vs+Prompt+Evaluation%3A+When+Braintrust+Isn%27t+Enough&subtitle=Prompt+evaluation+tools+like+Braintrust+excel+at+scoring+model+outputs.+Production+agents+need+trajectory+evals+on+real+tasks%3A+here%27s+how+to+know+when+to+add+sandboxed+agent+testing.&kind=blog 2026-06-11T00:00:00.000Z monthly 0.7 https://www.agentclash.dev/blog/ai-platform-lead-agent-release-gates https://www.agentclash.dev/og?title=The+AI+Platform+Lead%27s+Guide+to+Agent+Release+Gates&subtitle=Release+gates+for+AI+agents+need+frozen+workloads%2C+baseline+comparison%2C+replay+evidence%2C+and+CI+handoff.+A+guide+for+platform+leads+shipping+governed+agent+systems.&kind=blog 2026-06-11T00:00:00.000Z monthly 0.7 https://www.agentclash.dev/blog/coding-agent-benchmark-june-2026 https://www.agentclash.dev/og?title=Coding+agent+benchmark+%E2%80%94+June+2026&subtitle=Our+first+measured+public+benchmark%3A+four+GPT+generations+on+a+real+coding+task+with+frozen+challenge+packs%2C+full+trajectory+scoring%2C+and+replay+evidence.+Methodology%2C+scoreboard%2C+and+reproduction+steps.&kind=blog 2026-06-11T00:00:00.000Z monthly 0.7 https://www.agentclash.dev/blog/product-updates-june-2026 https://www.agentclash.dev/og?title=AgentClash+product+updates+%E2%80%94+June+2026&subtitle=Monthly+rollup+of+AgentClash+product+updates+from+May+and+June+2026%3A+datasets%2C+security+packs%2C+skills+distribution%2C+and+the+first+public+coding-agent+benchmark.+Full+timeline+on+the+changelog.&kind=blog 2026-06-11T00:00:00.000Z monthly 0.7 https://www.agentclash.dev/blog/ai-agent-approval-security-compliance https://www.agentclash.dev/og?title=How+to+Get+AI+Agent+Approval+from+Security+and+Compliance&subtitle=Security+and+compliance+teams+need+replay+evidence%2C+frozen+workloads%2C+and+gate+verdicts+before+they+approve+an+AI+agent.+A+practical+approval+checklist+for+platform+leads.&kind=blog 2026-06-10T00:00:00.000Z monthly 0.7 https://www.agentclash.dev/blog/benchmark-ai-agents-on-your-own-data https://www.agentclash.dev/og?title=How+to+Benchmark+AI+Agents+on+Your+Own+Data+%28Not+Public+Leaderboards%29&subtitle=Public+leaderboards+answer+a+general+model+question.+Shipping+agents+requires+benchmarks+on+your+workflows%2C+tools%2C+and+failure+modes%3A+a+practical+playbook.&kind=blog 2026-06-10T00:00:00.000Z monthly 0.7 https://www.agentclash.dev/blog/pass-k-reliability-enterprise-teams https://www.agentclash.dev/og?title=pass%40k%2C+pass%5Ek%2C+and+Reliability%3A+What+Enterprise+Teams+Should+Measure&subtitle=Enterprise+agent+releases+need+explicit+reliability+metrics.+A+practical+guide+to+pass%40k+and+pass%5Ek+for+platform+teams%2C+extending+the+pass%40k+vs+pass%5Ek+primer+with+release-gate+examples.&kind=blog 2026-06-09T00:00:00.000Z monthly 0.7 https://www.agentclash.dev/blog/evaluating-coding-agents-private-repos-checklist https://www.agentclash.dev/og?title=Evaluating+Coding+Agents+on+Private+Repos%3A+A+Practical+Checklist&subtitle=Coding+agents+on+private+repositories+need+evals+that+respect+your+layout%2C+tests%2C+and+policies+%28not+public+leaderboard+tasks%29.+A+checklist+for+platform+and+developer-experience+teams.&kind=blog 2026-06-08T00:00:00.000Z monthly 0.7 https://www.agentclash.dev/blog/agentclash-vs-langsmith-braintrust-production https://www.agentclash.dev/og?title=AgentClash+vs+LangSmith+vs+Braintrust+for+Production+Agent+Testing&subtitle=LangSmith+traces+chains%2C+Braintrust+scores+prompts%2C+AgentClash+races+tool-using+agents+on+real+tasks+with+replay+and+CI+gates%3A+an+honest+workflow+comparison+for+production+agent+testing.&kind=blog 2026-06-07T00:00:00.000Z monthly 0.7 https://www.agentclash.dev/blog/do-ai-models-cheat-by-brand https://www.agentclash.dev/og?title=I+Tried+to+Fingerprint+How+AI+Agents+Cheat+%E2%80%94+and+the+Brand+Didn%27t+Matter&subtitle=A+small+pilot+on+AgentClash%3A+8+frontier+models%2C+6+kinds+of+test-gaming%2C+192+runs.+The+surprise+wasn%27t+which+lab+built+the+model+%E2%80%94+it+was+that+how+an+agent+cheats+tracks+its+capability%2C+not+its+provider.+And+one+deleted+comment+made+the+cheating+disappear.&kind=blog 2026-06-07T00:00:00.000Z monthly 0.7 https://www.agentclash.dev/blog/pass-at-k-vs-pass-power-k https://www.agentclash.dev/og?title=pass%40k+vs+pass%5Ek%3A+What+Agent+Reliability+Metrics+Actually+Measure&subtitle=A+practical+guide+to+pass%40k+and+pass%5Ek+for+agent+evaluation+%E2%80%94+when+independent+retries+and+strict+success-over-trials+measure+different+kinds+of+reliability.&kind=blog 2026-06-06T00:00:00.000Z monthly 0.7 https://www.agentclash.dev/blog/why-agentclash-races-agents-head-to-head https://www.agentclash.dev/og?title=Why+AgentClash+Compares+Agents+Head-to-Head&subtitle=Staggered%2C+one-at-a-time+evals+compare+runs+that+never+faced+the+same+conditions.+AgentClash+runs+every+model+on+the+same+task+at+the+same+time+on+the+same+budget+%E2%80%94+here+is+why+concurrent+comparison+produces+a+fairer+verdict.&kind=blog 2026-06-03T00:00:00.000Z monthly 0.7 https://www.agentclash.dev/blog/how-agentclash-scores-agent-trajectories https://www.agentclash.dev/og?title=How+AgentClash+Scores+Agent+Trajectories&subtitle=Final-answer+grading+misses+how+an+agent+got+there.+Here+is+how+AgentClash+scores+the+whole+trajectory+with+deterministic+checks%2C+numeric+metrics%2C+behavioral+signals%2C+and+LLM+judges+%E2%80%94+then+aggregates+them+into+one+defensible+verdict.&kind=blog 2026-06-02T00:00:00.000Z monthly 0.7 https://www.agentclash.dev/blog/ai-agent-evaluation-regression-testing https://www.agentclash.dev/og?title=AI+Agent+Evaluation+Needs+Regression+Testing%2C+Not+Just+Benchmarks&subtitle=A+practical+guide+to+AI+agent+evaluation+with+real-task+workloads%2C+replay+evidence%2C+scorecards%2C+challenge+packs%2C+and+CI+regression+gates.&kind=blog 2026-05-07T00:00:00.000Z monthly 0.7 https://www.agentclash.dev/blog/why-we-built-agentclash https://www.agentclash.dev/og?title=Why+We+Built+AgentClash&subtitle=Static+benchmarks+leak.+Leaderboards+reward+hype.+We+built+something+different.&kind=blog 2026-03-23T00:00:00.000Z monthly 0.7 https://www.agentclash.dev/docs/architecture/data-model https://www.agentclash.dev/og?title=Data+Model&subtitle=Learn+the+core+entities+behind+workspaces%2C+deployments%2C+challenge+packs%2C+runs%2C+and+evidence+in+AgentClash.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/architecture/evidence-loop https://www.agentclash.dev/og?title=Evidence+Loop&subtitle=See+how+AgentClash+moves+from+execution+events+to+replay%2C+scorecards%2C+and+future+evaluation+improvement.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/architecture/frontend https://www.agentclash.dev/og?title=Frontend+Architecture&subtitle=The+Next.js+app+is+doing+three+jobs+at+once%3A+public+marketing+pages%2C+authenticated+product+surfaces%2C+and+now+a+public+docs+experience.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/architecture/orchestration https://www.agentclash.dev/og?title=Orchestration&subtitle=The+API+server+accepts+the+request%2C+but+Temporal+and+the+worker+are+what+make+long-running+run+execution+survivable.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/architecture/overview https://www.agentclash.dev/og?title=Architecture+Overview&subtitle=AgentClash+is+a+monorepo+with+a+small+number+of+load-bearing+runtime+components.+This+page+names+them+and+explains+why+they+are+split+this+way.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/architecture/sandbox-layer https://www.agentclash.dev/og?title=Sandbox+Layer&subtitle=Understand+why+AgentClash+isolates+execution+behind+a+sandbox+provider+boundary+and+how+E2B%2C+Docker%2C+and+Kubernetes+fit.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/challenge-packs/bundle-yaml-reference https://www.agentclash.dev/og?title=Bundle+YAML+reference&subtitle=Structured+reference+for+challenge-pack+bundles+as+parsed+by+backend%2Finternal%2Fchallengepack.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/challenge-packs/eval-workflows-and-gates https://www.agentclash.dev/og?title=Eval+workflows+%26+gates&subtitle=CLI-first+eval+commands%2C+baselines%2C+scorecards%2C+comparisons%2C+and+release+gates+as+implemented+in+cli%2Fcmd.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/challenge-packs/evaluation-spec-reference https://www.agentclash.dev/og?title=Evaluation+spec+reference&subtitle=Validators%2C+metrics%2C+behavioral+signals%2C+runtime+limits%2C+and+scorecard+semantics+from+backend%2Finternal%2Fscoring.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/challenge-packs https://www.agentclash.dev/og?title=Challenge+pack+documentation&subtitle=Deep%2C+consumer-facing+YAML+and+runtime+reference+keyed+to+the+parsers%2C+validators%2C+and+workers+in+this+repository.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/challenge-packs/input-sets-and-cases https://www.agentclash.dev/og?title=Input+sets+%26+cases&subtitle=How+cases+bind+challenges%2C+structured+inputs%2C+expectations%2C+assets%2C+and+legacy+payloads%E2%80%94grounded+in+challengepack.CaseDefinition.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/challenge-packs/llm-judges https://www.agentclash.dev/og?title=LLM+judges&subtitle=LLM-as-judge+declarations%2C+rubric%2Fassertion+modes%2C+consensus%2C+budgets%2C+evidence+wiring%E2%80%94straight+from+scoring%2Fspec.go+and+validation_judges.go.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/challenge-packs/multi-turn https://www.agentclash.dev/og?title=Multi-turn+challenge+packs&subtitle=Hybrid+multi_turn+execution+with+scripted%2C+LLM%2C+and+human+user-simulator+phases%2C+operator+APIs%2C+and+calibration+reviews.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/challenge-packs/sandbox-and-e2b https://www.agentclash.dev/og?title=Sandbox+%26+E2B&subtitle=Pack+sandbox+fields%2C+worker+sandbox+provider+selection%2C+and+how+native+execution+reaches+E2B+today.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/challenge-packs/tools-primitives-and-policy https://www.agentclash.dev/og?title=Tools%2C+primitives+%26+policy&subtitle=How+tool_policy+and+tools.custom+map+to+engine+primitives+in+backend%2Finternal%2Fengine+and+sandbox.ToolPolicy.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/concepts/agents-and-deployments https://www.agentclash.dev/og?title=Agents+and+Deployments&subtitle=Understand+how+AgentClash+turns+a+build+plus+runtime%2Fprovider+resources+into+a+concrete+deployment+that+can+be+scheduled+into+a+run.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/concepts/artifacts https://www.agentclash.dev/og?title=Artifacts&subtitle=Understand+workspace+artifacts%2C+pack+assets%2C+run+evidence+files%2C+and+how+downloads+are+signed+and+delivered.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/concepts/challenge-packs-and-inputs https://www.agentclash.dev/og?title=Challenge+Packs+and+Inputs&subtitle=Learn+what+a+challenge+pack+really+is+in+AgentClash%2C+how+the+bundle+is+structured%2C+and+how+inputs+become+runnable+cases.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/concepts/replay-and-scorecards https://www.agentclash.dev/og?title=Replay+and+Scorecards&subtitle=Understand+how+run+events+become+a+readable+timeline%2C+a+defensible+score%2C+and+a+reusable+evidence+trail.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/concepts/runs-and-evals https://www.agentclash.dev/og?title=Runs+and+Evals&subtitle=The+product+language+around+runs+and+evals+is+easy+to+blur.+The+current+codebase+makes+one+distinction+especially+important.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/concepts/tools-network-and-secrets https://www.agentclash.dev/og?title=Tools%2C+Network%2C+and+Secrets&subtitle=Learn+the+difference+between+workspace+tools%2C+pack-defined+tools%2C+and+engine+primitives%2C+and+how+network+and+secret+handling+are+constrained.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/concepts/try-cli https://www.agentclash.dev/og?title=Try+CLI+%E2%80%94+interactive+terminal+demos&subtitle=AgentClash+primitive+for+one-click+disposable+terminal+demos.+README+badges%2C+E2B+sandboxes%2C+xterm.js.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/concepts/voice-artifact-contracts https://www.agentclash.dev/og?title=Voice+Artifact+Contracts&subtitle=Standard+artifact+and+report+contracts+for+evaluating+voice+agents+across+providers%2C+transports%2C+and+media+pipelines.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/contributing/codebase-tour https://www.agentclash.dev/og?title=Codebase+Tour&subtitle=Map+the+main+AgentClash+modules+before+you+start+changing+workflows%2C+APIs%2C+or+the+web+UI.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/contributing/setup https://www.agentclash.dev/og?title=Contributor+Setup&subtitle=Clone+the+repo%2C+bring+up+the+local+stack%2C+and+pick+the+fastest+development+loop+for+the+part+of+AgentClash+you+are+changing.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/contributing/testing https://www.agentclash.dev/og?title=Testing&subtitle=Choose+the+smallest+useful+validation+loop+and+use+review+checkpoints+to+keep+implementation+work+scoped.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/fleet/budgets-and-scanners https://www.agentclash.dev/og?title=Budgets+and+scanners&subtitle=Cap+eval-set+spend%2C+emergency-stop+a+workspace%2C+and+run+built-in+transcript+scanners+after+completion.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/fleet/cli-evalset https://www.agentclash.dev/og?title=CLI+evalset+workflow&subtitle=Submit%2C+follow%2C+log%2C+report%2C+and+cancel+Fleet+eval+sets+with+agentclash+evalset.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/fleet/eval-set-manifests https://www.agentclash.dev/og?title=Eval-set+manifests&subtitle=Author+evalset%2Fv1+YAML+for+packs+%C3%97+agents+%C3%97+models+%C3%97+repeats%2C+dry-run+expansion%2C+and+combination+caps.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/fleet https://www.agentclash.dev/og?title=Fleet+overview&subtitle=Run+packs+%C3%97+agents+%C3%97+models+%C3%97+repeats+as+one+eval+set+with+a+live+matrix%2C+warehouse+exports%2C+budgets%2C+and+transcript+scanners.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/fleet/matrix-and-warehouse https://www.agentclash.dev/og?title=Matrix+and+warehouse&subtitle=Watch+live+eval-set+cells+in+the+web+UI+and+export+searchable+case+results+from+the+warehouse.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/fleet/self-host-scale https://www.agentclash.dev/og?title=Self-host+at+scale&subtitle=Helm+chart%2C+KEDA+workers%2C+Kubernetes+sandboxes%2C+capacity+limits%2C+LLM+throttle%2C+and+Fleet+observability+for+self-hosted+AgentClash.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/getting-started/first-eval https://www.agentclash.dev/og?title=First+Eval+Walkthrough&subtitle=Use+the+current+seeded+local+path+to+create+a+run%2C+stream+events%2C+and+inspect+ranking+output+without+inventing+setup+that+is+not+in+the+repo.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/getting-started/quickstart https://www.agentclash.dev/og?title=Hosted+Quickstart&subtitle=Validate+the+CLI+against+the+hosted+production+backend%2C+set+a+workspace%2C+and+get+to+your+first+runnable+command+in+a+few+minutes.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/getting-started/self-host https://www.agentclash.dev/og?title=Self-Host+Starter&subtitle=Bring+up+the+local+AgentClash+stack+with+the+repo%E2%80%99s+existing+scripts+and+understand+which+dependencies+are+mandatory+versus+optional.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/guides/ci-cd-agent-gates https://www.agentclash.dev/og?title=CI%2FCD+Agent+Gates&subtitle=Use+a+repo-tracked+AgentClash+CI+manifest+to+define+which+agent+revision%2C+workload%2C+baseline%2C+and+gate+a+pull+request+should+run.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/guides/ci-cd-workload-recipes https://www.agentclash.dev/og?title=CI%2FCD+Workload+Recipes&subtitle=Choose+realistic+AgentClash+CI+workloads+for+coding%2C+research%2C+support%2C+ops%2C+and+long-horizon+agents.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/guides/configure-runtime-resources https://www.agentclash.dev/og?title=Configure+Runtime+Resources&subtitle=Create+secrets%2C+provider+accounts%2C+runtime+profiles%2C+and+model-backed+deployments+in+the+order+the+current+product+expects.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/guides/dataset-ci-gates https://www.agentclash.dev/og?title=Dataset+CI+Gates&subtitle=Record+dataset+eval+baselines%2C+sync+examples+into+regression+suites%2C+and+fail+CI+when+a+candidate+run+regresses.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/guides/datasets-overview https://www.agentclash.dev/og?title=Datasets+overview&subtitle=Generate+pinned+dataset+evals%2C+record+baselines%2C+sync+regression+suites%2C+and+gate+releases+with+agentclash+dataset+commands.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/guides/interpret-results https://www.agentclash.dev/og?title=Interpret+Results&subtitle=Read+AgentClash+run+output+from+top-line+score+to+raw+replay+evidence+without+getting+lost.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/guides/security-evaluation https://www.agentclash.dev/og?title=Security+evaluation&subtitle=Stress-run+security+challenge+packs%2C+score+planted-secret+leaks+and+adversarial+acceptance%2C+and+gate+releases+with+agentclash+security+commands.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/guides/synthetic-dataset-generation https://www.agentclash.dev/og?title=Synthetic+dataset+generation&subtitle=Generate+high-signal+synthetic+examples+with+Self-Instruct+or+Agentic+Self-Instruct+weak-vs-strong+loops+in+AgentClash+workspaces.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/guides/use-with-ai-tools https://www.agentclash.dev/og?title=Use+with+AI+Tools&subtitle=Feed+AgentClash+docs+into+ChatGPT%2C+Codex%2C+Claude+Code%2C+and+similar+tools+using+llms.txt+and+markdown+exports%2C+and+install+the+AgentClash+Agent+Skills.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/guides/write-a-challenge-pack https://www.agentclash.dev/og?title=Write+a+Challenge+Pack&subtitle=Author+a+challenge-pack+bundle+in+YAML%2C+validate+it+against+the+current+parser%2C+and+publish+it+into+a+workspace.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/reference/cli https://www.agentclash.dev/og?title=CLI+Reference&subtitle=Commands%2C+flags%2C+and+command+groups+generated+from+the+current+Cobra+CLI+source.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/reference/config https://www.agentclash.dev/og?title=Config+Reference&subtitle=Environment+variables+and+config+precedence+generated+from+the+current+source+readers.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs https://www.agentclash.dev/og?title=AgentClash+Documentation&subtitle=Run+agents+head-to-head+on+real+tasks%2C+inspect+the+telemetry%2C+and+understand+the+system+without+wading+through+roadmap+fiction.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.85 https://www.agentclash.dev/docs/agent-skills https://www.agentclash.dev/og?title=Agent+Skills&subtitle=Copyable+AgentClash+skills+for+coding+agents%2C+exposed+as+docs+pages+and+markdown+exports.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/agent-skills/challenge-pack-skills https://www.agentclash.dev/og?title=Challenge+Pack+Skills&subtitle=Focused+skills+for+planning%2C+authoring%2C+scoring%2C+judging%2C+tooling%2C+artifacts%2C+validation%2C+and+publishing+challenge+packs.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/agent-skills/agent-build-skills https://www.agentclash.dev/og?title=Agent+Build+Skills&subtitle=Focused+skills+for+agent+build+specs%2C+deployments%2C+runtime+resources%2C+provider+accounts%2C+model+aliases%2C+and+secrets.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/agent-skills/agent-build-skills/agentclash-agent-build-author https://www.agentclash.dev/og?title=Agent+Build+Author+Skill&subtitle=Use+when+creating%2C+editing%2C+validating%2C+or+readying+AgentClash+agent+builds+and+build+versions%2C+including+agent+identity%2C+spec+JSON%2C+prompts%2C+model%2Fruntime+expectations%2C+tool+bindings%2C+and+version+readiness.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/agent-skills/agent-build-skills/agentclash-agent-deployment-setup https://www.agentclash.dev/og?title=Agent+Deployment+Setup+Skill&subtitle=Use+when+creating%2C+selecting%2C+or+diagnosing+AgentClash+agent+deployments+for+runs%2C+including+ready+build+versions%2C+runtime+profiles%2C+provider%2Fmodel+wiring%2C+deployment+IDs%2C+workspace+context%2C+and+run+compatibility.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/agent-skills/agent-build-skills/agentclash-runtime-resources-setup https://www.agentclash.dev/og?title=Runtime+Resources+Setup+Skill&subtitle=Use+when+configuring+AgentClash+workspace+secrets%2C+provider+accounts%2C+provider+models%2C+runtime+profiles%2C+workspace+tools%2C+and+readiness+checks+required+before+agent+builds%2C+deployments%2C+evals%2C+or+runs.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/agent-skills/agentclash-agent-harness-setup https://www.agentclash.dev/og?title=Agent+Harness+Setup+Skill&subtitle=Use+when+creating%2C+running%2C+or+ranking+Agent+Harness+coding-agent+tasks+via+the+CLI%2C+including+harness+specs%2C+E2B+runner+kinds%2C+suite+task+banks%2C+executions%2C+failure+review%2C+and+promote-to-task+flows.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/agent-skills/agentclash-ci-release-gate https://www.agentclash.dev/og?title=CI+Release+Gate+Skill&subtitle=Use+when+wiring+AgentClash+manifest-based+CI+gates%2C+deciding+whether+a+PR+should+run+AgentClash%2C+resolving+baselines%2C+running+%60agentclash+ci+run%60%2C+interpreting+gate+exit+codes%2C+collecting+CI+artifacts%2C+or+configuring+regression+promotion+policy+in+GitHub+Actions.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/agent-skills/agentclash-cli-setup https://www.agentclash.dev/og?title=CLI+Setup+Skill&subtitle=Use+when+configuring+the+AgentClash+CLI%2C+authenticating+with+device+login+or+tokens%2C+selecting+a+workspace%2C+saving+default+config+with+link%2C+creating+project+config+with+init%2C+resolving+API+URL+precedence%2C+or+diagnosing+CLI+access+against+production%2C+local%2C+or+self-hosted+backends.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/agent-skills/agentclash-compare-and-triage https://www.agentclash.dev/og?title=Compare+And+Triage+Skill&subtitle=Use+when+comparing+baseline+vs+candidate+AgentClash+runs%2C+evaluating+release+gates%2C+managing+workspace+baseline+bookmarks%2C+or+building+a+replay+triage+envelope+after+an+eval+completes.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/agent-skills/agentclash-dataset-workflows https://www.agentclash.dev/og?title=Dataset+Workflows+Skill&subtitle=Use+when+managing+AgentClash+datasets+via+CLI+%E2%80%94+create+versions%2C+import%2Fexport+examples%2C+run+evals%2C+CI+gates%2C+synthetic+generation%2C+trace+import%2C+candidate+review%2C+and+regression+suite+sync.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/agent-skills/agentclash-eval-runner https://www.agentclash.dev/og?title=Eval+Runner+Skill&subtitle=Use+when+starting%2C+following%2C+inspecting%2C+or+reporting+AgentClash+eval+runs+with+the+CLI%2C+especially+eval+start%2C+run+create%2C+deployment+selection%2C+input+set+selection%2C+suite-only+scopes%2C+repetitions%2C+events%2C+rankings%2C+failures%2C+and+scorecards.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/agent-skills/agentclash-hub https://www.agentclash.dev/og?title=Hub+Skill&subtitle=Use+when+starting+any+AgentClash+eval%2C+CLI%2C+or+challenge-pack+task.+Load+this+skill+first+for+the+full+workflow+map%2C+skill+dependency+order%2C+product+UI+links%2C+hosted+defaults%2C+and+pointers+to+every+other+AgentClash+skill.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/agent-skills/agentclash-multi-turn-operator https://www.agentclash.dev/og?title=Multi+Turn+Operator+Skill&subtitle=Use+when+a+multi_turn+challenge+pack+run+agent+is+awaiting+human+input+and+you+need+to+check+turn+status+or+submit+an+operator+message+with+agentclash+run+turn.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/agent-skills/agentclash-prompt-eval-playground https://www.agentclash.dev/og?title=Prompt+Eval+Playground+Skill&subtitle=Use+when+scaffolding%2C+validating%2C+or+running+prompt+eval+YAML+configs+and+managing+playground+experiments%2C+test+cases%2C+and+prompt+variants+via+the+AgentClash+CLI.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/agent-skills/agentclash-quickstart https://www.agentclash.dev/og?title=Quickstart+Skill&subtitle=Use+when+checking+whether+a+workspace+is+ready+to+run+AgentClash+evals%2C+interpreting+quickstart+readiness+checks%2C+or+choosing+the+next+CLI+command+after+auth+and+workspace+selection.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/agent-skills/agentclash-regression-flywheel https://www.agentclash.dev/og?title=Regression+Flywheel+Skill&subtitle=Use+when+inspecting+AgentClash+run+failure-review+items%2C+promoting+useful+failures+into+regression+suites%2C+editing+regression+suites+or+cases%2C+and+verifying+suite-only+reruns.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/agent-skills/agentclash-scorecard-reader https://www.agentclash.dev/og?title=Scorecard+Reader+Skill&subtitle=Use+when+interpreting+AgentClash+rankings%2C+scorecards%2C+replay+timelines%2C+artifacts%2C+LLM+judge+results%2C+or+failure-review+evidence+into+source-backed+findings+and+next+actions.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/agent-skills/agentclash-security-evaluation https://www.agentclash.dev/og?title=Security+Evaluation+Skill&subtitle=Use+when+running+client-side+security+stress+harnesses+against+security+challenge+packs%2C+measuring+leak+posture%2C+Agent+Vault+routing%2C+or+HashiCorp+Vault+runtime+leaks+with+agentclash+security+commands.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/agent-skills/agentclash-workspace-admin https://www.agentclash.dev/og?title=Workspace+Admin+Skill&subtitle=Use+when+creating+or+administering+AgentClash+organizations+and+workspaces%2C+inviting+members%2C+updating+roles%2C+or+binding+default+workspace+context+beyond+basic+CLI+login.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/agent-skills/challenge-pack-skills/agentclash-challenge-pack-artifacts https://www.agentclash.dev/og?title=Challenge+Pack+Artifacts+Skill&subtitle=Use+when+specifying+AgentClash+challenge+pack+assets%2C+artifact+references%2C+produced+file+captures%2C+evidence+references%2C+artifact+upload%2Fdownload+expectations%2C+and+review-only+evidence.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/agent-skills/challenge-pack-skills/agentclash-challenge-pack-input-sets https://www.agentclash.dev/og?title=Challenge+Pack+Input+Sets+Skill&subtitle=Use+when+designing+AgentClash+challenge+pack+cases+and+input+sets+for+smoke%2C+full+benchmark%2C+regression%2C+edge-case%2C+or+CI+suite-only+coverage.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/agent-skills/challenge-pack-skills/agentclash-challenge-pack-llm-judges https://www.agentclash.dev/og?title=Challenge+Pack+LLM+Judges+Skill&subtitle=Use+when+configuring+AgentClash+LLM-as-judge+scoring%2C+judge+prompts%2C+rubrics%2C+assertion%2Freference%2Fn-wise+modes%2C+evidence+inputs%2C+scorecard+dimensions%2C+abstention+behavior%2C+and+judge+result+interpretation.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/agent-skills/challenge-pack-skills/agentclash-challenge-pack-planner https://www.agentclash.dev/og?title=Challenge+Pack+Planner+Skill&subtitle=Use+when+turning+a+vague+AgentClash+evaluation+idea+into+a+source-backed+challenge+pack+plan+with+task+boundaries%2C+target+agents%2C+cases%2C+input+sets%2C+scoring+strategy%2C+tools%2C+artifacts%2C+runtime+policy%2C+validation+criteria%2C+and+handoff+steps.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/agent-skills/challenge-pack-skills/agentclash-challenge-pack-scoring-validators https://www.agentclash.dev/og?title=Challenge+Pack+Scoring+Validators+Skill&subtitle=Use+when+defining+deterministic+AgentClash+scoring+validators%2C+scorecard+dimensions%2C+evidence+sources%2C+pass%2Ffail+rules%2C+numeric+metrics%2C+file+checks%2C+and+validator+result+interpretation.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/agent-skills/challenge-pack-skills/agentclash-challenge-pack-tools-sandbox https://www.agentclash.dev/og?title=Challenge+Pack+Tools+Sandbox+Skill&subtitle=Use+when+defining+AgentClash+challenge+pack+tool+access%2C+sandbox+runtime+needs%2C+filesystem+expectations%2C+network+policy%2C+command+execution%2C+and+secret+references.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/agent-skills/challenge-pack-skills/agentclash-challenge-pack-validation-publish https://www.agentclash.dev/og?title=Challenge+Pack+Validation+Publish+Skill&subtitle=Use+when+validating+AgentClash+challenge+pack+YAML%2C+fixing+schema%2Fscoring%2Ftool%2Fasset+errors%2C+publishing+runnable+pack+versions%2C+recording+returned+IDs%2C+and+preparing+next+eval+commands.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/docs/agent-skills/challenge-pack-skills/agentclash-challenge-pack-yaml-author https://www.agentclash.dev/og?title=Challenge+Pack+YAML+Author+Skill&subtitle=Use+when+writing+or+editing+AgentClash+challenge+pack+YAML%2C+including+pack%2Fversion+metadata%2C+execution+mode%2C+challenges%2C+cases%2C+input+sets%2C+scoring+blocks%2C+tools%2C+sandbox+settings%2C+assets%2C+and+validation+handoff.&kind=docs 2026-08-20T13:13:17.624Z weekly 0.75 https://www.agentclash.dev/benchmarks/gpt-generations-expression-evaluator https://www.agentclash.dev/og?title=We+raced+four+GPT+generations+on+a+real+coding+task+%E2%80%94+GPT-5.4+won+on+efficiency&subtitle=A+head-to-head+AgentClash+comparison+of+GPT-4.1%2C+GPT-5%2C+GPT-5.4%2C+and+GPT-5.5+on+a+real+agentic+coding+task+%E2%80%94+building+an+integer+expression+evaluator+with+truncating+division+%E2%80%94+scored+on+correctness%2C+reliability%2C+and+token+efficiency.&kind=benchmark 2026-06-07T00:00:00.000Z monthly 0.75