Agent Skill evaluation harness for paired variants, trace artifacts, and runner adapters
adewale/
skill-eval-harness
adewale/skill-eval-harnessHarnesses
73
oxbshw/watch-skillHarnesses
Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work with deterministic contracts, not model opinion. DeepWatch is the agent workspace built on DeepSeek Harness. Python + npm, MCP, CLI, REST, Web.
362
blogminhquy/
javis-os
blogminhquy/javis-osHarnesses
Self-hosted agent OS with skills, workflows, MCP, and second brain storage.
194
hoangsonww/
AI-Agents-Orchestrator
hoangsonww/AI-Agents-OrchestratorHarnesses
🪈 Intelligent orchestration system that coordinates multiple AI coding assistants (Claude, Codex, Gemini CLI, Copilot CLI) to collaborate on complex software development tasks via REPL or a Vue/Nuxt UI dashboard. Also includes an Agentic Team runtime with role-based multi-agent open communication & lead-gated final responses.
84