{"id":49481779,"url":"https://github.com/haxsysgit/haxaml","last_synced_at":"2026-04-30T23:00:24.133Z","repository":{"id":354368391,"uuid":"1222921310","full_name":"haxsysgit/haxaml","owner":"haxsysgit","description":"Deterministic agent-management framework that implements FRAME governance for AI-assisted software development.","archived":false,"fork":false,"pushed_at":"2026-04-28T08:17:22.000Z","size":463,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-28T10:16:02.726Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/haxsysgit.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-04-27T20:52:52.000Z","updated_at":"2026-04-28T08:17:25.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/haxsysgit/haxaml","commit_stats":null,"previous_names":["haxsysgit/haxaml"],"tags_count":6,"template":false,"template_full_name":null,"purl":"pkg:github/haxsysgit/haxaml","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/haxsysgit%2Fhaxaml","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/haxsysgit%2Fhaxaml/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/haxsysgit%2Fhaxaml/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/haxsysgit%2Fhaxaml/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/haxsysgit","download_url":"https://codeload.github.com/haxsysgit/haxaml/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/haxsysgit%2Fhaxaml/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32407176,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-28T19:38:08.556Z","status":"online","status_checked_at":"2026-04-29T02:00:06.602Z","response_time":110,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":[],"created_at":"2026-04-30T23:00:15.569Z","updated_at":"2026-04-30T23:00:23.698Z","avatar_url":"https://github.com/haxsysgit.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Haxaml\n\n[![PyPI version](https://img.shields.io/pypi/v/haxaml.svg)](https://pypi.org/project/haxaml/)\n\nHaxaml is an LLM-first governance layer for coding agents.\n\nIt is an MCP-first project: agents are expected to work through the Haxaml MCP server, with the CLI available mainly for local setup and fallback.\n\nLatest release: `0.5.0`.\n\nHaxaml gives agents a deterministic project memory model called **FRAME**, plus MCP tools that make context, rules, verification, and handoff explicit during real work.\n\n## Why It Exists\n\nAgent instructions are usually scattered across prompt files, chat history, local conventions, and whatever the current model remembers. That works until the project grows, the session rolls over, or a different agent enters the repo.\n\nHaxaml keeps the operational truth in versioned project files and exposes it through a predictable workflow. Agents can ask for the right context, follow project rules, verify before claiming success, and record what changed.\n\n## What Agents Get\n\n- Project facts, rules, history, expectations, and impact maps in `.haxaml/`\n- Task-specific context packs instead of giant prompt dumps\n- Validation and reconcile checks before state is trusted\n- Verify/record gates for governed work\n- Export paths for native agent files such as `AGENTS.md`, `CLAUDE.md`, Cursor rules, Copilot instructions, and Gemini guidance\n\n## Install\n\n```bash\nuvx haxaml-mcp\n```\n\nFor persistent local installs:\n\n```bash\nuv tool install haxaml-mcp\n```\n\n## MCP Start\n\nConfigure your MCP client to launch `haxaml-mcp` with `HAXAML_PROJECT_DIR` set to the project root. See [MCP.md](https://github.com/haxsysgit/haxaml/blob/main/MCP.md) for the human/operator guide.\n\nOnce connected, agents can initialize and validate through MCP tools:\n\n- `haxaml_init`\n- `haxaml_validate`\n\nOptional CLI fallback for local setup:\n\n```bash\nhaxaml init\nhaxaml validate\n```\n\n## Bootstrap Prompt\n\nPaste this into your native agent instruction file (`AGENTS.md`, `CLAUDE.md`, `GEMINI.md`, `.github/copilot-instructions.md`, etc.):\n\n```md\nThis repository uses Haxaml for agent governance.\n\nUse the Haxaml MCP server for governed project work.\nBefore governed project work, call haxaml_about(project_dir='.') once in the active MCP session.\nFollow the workflow returned by that tool.\nDo not edit .haxaml/* for utility or side tasks that are not governed project work.\n```\n\n## FRAME Files\n\n- `.haxaml/facts.yaml` - project truth\n- `.haxaml/rules.yaml` - agent operating rules\n- `.haxaml/acts.yaml` - execution diary and decisions\n- `.haxaml/expect.yaml` - run plan and milestones\n- `.haxaml/map.yaml` - optional module ownership and impact map\n\n## Docs\n\n- [learn/FRAME.md](https://github.com/haxsysgit/haxaml/blob/main/learn/FRAME.md) - FRAME memory model\n- [learn/haxaml.md](https://github.com/haxsysgit/haxaml/blob/main/learn/haxaml.md) - how Haxaml makes FRAME operational\n- [MCP.md](https://github.com/haxsysgit/haxaml/blob/main/MCP.md) - MCP setup and operator guide\n- [v1.0_Roadmap.md](https://github.com/haxsysgit/haxaml/blob/main/v1.0_Roadmap.md) - roadmap from `0.6.0` to `1.0`\n- [docs/architecture.md](https://github.com/haxsysgit/haxaml/blob/main/docs/architecture.md) - module layout and MCP split overview\n- [docs/mcp-tool-reference.md](https://github.com/haxsysgit/haxaml/blob/main/docs/mcp-tool-reference.md) - compact MCP tool and resource index\n- [CONTRIBUTING.md](https://github.com/haxsysgit/haxaml/blob/main/CONTRIBUTING.md) - contributor workflow and expectations\n- [examples/minimal-governed-flow](https://github.com/haxsysgit/haxaml/tree/main/examples/minimal-governed-flow) - minimal FRAME project for governed-flow smoke tests\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhaxsysgit%2Fhaxaml","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhaxsysgit%2Fhaxaml","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhaxsysgit%2Fhaxaml/lists"}