{"id":50140561,"url":"https://github.com/supernovae/open-cot","last_synced_at":"2026-05-24T01:03:26.623Z","repository":{"id":351574432,"uuid":"1210490526","full_name":"supernovae/open-cot","owner":"supernovae","description":"Open-CoT is a model-agnostic cognitive control plane that standardizes the trusted contract between model output, harness/runtime enforcement, policy, delegation, tool execution, provenance, and audit.","archived":false,"fork":false,"pushed_at":"2026-04-27T16:23:22.000Z","size":766,"stargazers_count":5,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-27T16:28:57.508Z","etag":null,"topics":["agent","agentic","agentic-ai","benchmarks","control-plane","datasets","harness","harness-execution-layer","harness-framework","llm","schema"],"latest_commit_sha":null,"homepage":"","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/supernovae.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"docs/contributing.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":"docs/governance-rfc-lifecycle.md","roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":"docs/maintainers.md","copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-04-14T13:20:01.000Z","updated_at":"2026-04-27T16:23:25.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/supernovae/open-cot","commit_stats":null,"previous_names":["supernovae/open-cot"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/supernovae/open-cot","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/supernovae%2Fopen-cot","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/supernovae%2Fopen-cot/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/supernovae%2Fopen-cot/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/supernovae%2Fopen-cot/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/supernovae","download_url":"https://codeload.github.com/supernovae/open-cot/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/supernovae%2Fopen-cot/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33417491,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-23T22:14:44.296Z","status":"ssl_error","status_checked_at":"2026-05-23T22:14:43.778Z","response_time":53,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agent","agentic","agentic-ai","benchmarks","control-plane","datasets","harness","harness-execution-layer","harness-framework","llm","schema"],"created_at":"2026-05-24T01:03:23.019Z","updated_at":"2026-05-24T01:03:26.603Z","avatar_url":"https://github.com/supernovae.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Open CoT\n\nOpen CoT is **Cognitive Operations Theory**: a compact, schema-first standard for the boundary between cognition and execution.\n\nThe model contributes a typed cognitive artifact. Runtime code validates, authorizes, executes endpoint capabilities, records observations, and reconciles final state. Reasoning remains important as evidence, but it is never authority.\n\n## Core RFCs\n\nThe active RFC set is intentionally small and sequential:\n\n1. Cognitive Artifact \u0026 Reasoning Evidence\n2. Capability Snapshot \u0026 Endpoint Descriptor\n3. Execution Intent \u0026 Endpoint Invocation\n4. Policy Gate \u0026 Permission Evaluation\n5. Observation, Receipt \u0026 Audit Evidence\n6. Reconciliation Result \u0026 Error Taxonomy\n7. Runtime Boundary \u0026 Cognitive Pipeline\n8. Budget, Cost \u0026 Temporal Bounds\n9. Requester Identity \u0026 Governance Context\n10. Human Approval, Yield \u0026 Resume\n11. Conformance, Registry \u0026 Compatibility Rules\n12. Compact Context Serialization\n\nSchemas are embedded in the RFC markdown and generated into `schemas/` with `python3 tools/sync_schemas_from_rfcs.py`.\n\n## Validate\n\n```bash\npython3 tools/sync_schemas_from_rfcs.py\npython3 tools/validate.py\ncd harness \u0026\u0026 npm test\n```\n\nOpen Lagrange is the opinionated implementation proving this interface under durable execution, policy gates, endpoint execution, and reconciliation.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsupernovae%2Fopen-cot","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsupernovae%2Fopen-cot","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsupernovae%2Fopen-cot/lists"}