{"id":49712647,"url":"https://github.com/codehamr/codehamr","last_synced_at":"2026-05-29T17:00:24.695Z","repository":{"id":354645941,"uuid":"1224508792","full_name":"codehamr/codehamr","owner":"codehamr","description":"A minimal, local-first coding agent for the terminal.","archived":false,"fork":false,"pushed_at":"2026-05-29T16:09:09.000Z","size":582,"stargazers_count":49,"open_issues_count":0,"forks_count":3,"subscribers_count":2,"default_branch":"main","last_synced_at":"2026-05-29T16:21:44.859Z","etag":null,"topics":["ai-agent","coding-agent","local-llm"],"latest_commit_sha":null,"homepage":"https://codehamr.com","language":"Go","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/codehamr.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2026-04-29T10:56:17.000Z","updated_at":"2026-05-29T16:08:55.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/codehamr/codehamr","commit_stats":null,"previous_names":["codehamr/codehamr"],"tags_count":9,"template":false,"template_full_name":null,"purl":"pkg:github/codehamr/codehamr","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codehamr%2Fcodehamr","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codehamr%2Fcodehamr/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codehamr%2Fcodehamr/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codehamr%2Fcodehamr/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/codehamr","download_url":"https://codeload.github.com/codehamr/codehamr/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codehamr%2Fcodehamr/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33662205,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-05-29T02:00:06.066Z","response_time":107,"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":["ai-agent","coding-agent","local-llm"],"created_at":"2026-05-08T17:02:43.040Z","updated_at":"2026-05-29T17:00:24.687Z","avatar_url":"https://github.com/codehamr.png","language":"Go","funding_links":[],"categories":[],"sub_categories":[],"readme":"# codehamr\n\nA minimal coding agent for the terminal. Built for local LLMs, also\nruns on OpenAI compatible endpoints.\n\n## Simplicity\n\nA coding agent built for local LLMs has to make different decisions\nthan one built for frontier cloud models. Context is precious. Every\ntool call has to earn its place. codehamr picks simplicity over\ncomplexity, on purpose. The agent stays small so the context window\nstays yours.\n\nThree slash commands, one embedded system prompt, no router, no\nsub-agents, no skill system, no MCP. That's it.\n\nThe agent runs in one deterministic loop, internally called *GYSD*\n(Get Your Shit Done), where every turn ends with one of three tools:\n`verify` (run a check), `done` (claim completion, must quote a passing\nverify as proof), or `ask` (yield back to you). No hallucinated success.\n\n## Install\n\nLinux, MacOS:\n\n```bash\ncurl -fsSL https://codehamr.com/install.sh | bash\n```\n\nWindows:\n\n```cmd\ncurl -fsSL https://codehamr.com/install.cmd -o install.cmd \u0026\u0026 install.cmd\n```\n\nThen run `codehamr` in your project.\n\n\u003e **Warning:** AI systems like codehamr run model-generated shell commands with full filesystem access. Best run inside safe sandboxes like devcontainers or isolated VMs.\n\n## Config\n\nOn first run codehamr creates `.codehamr/config.yaml` for your\nprofiles. The system prompt is embedded in the binary, not on disk.\nProject specific rules go straight into the chat: tell the agent\nwhat matters, the conversation carries it.\n\n```yaml\n# codehamr configuration\n#\n# Running codehamr in a devcontainer / WSL2 with Ollama on the host:\n# swap 'http://localhost:11434' with 'http://host.docker.internal:11434' below.\n\nactive: local\nmodels:\n    local:\n        llm: qwen3.6:27b\n        url: http://localhost:11434\n        key: \"\"\n        context_size: 131072\n    openai:\n        llm: gpt-5.5\n        url: https://api.openai.com\n        key: sk-...\n        context_size: 131072\n    hamrpass:\n        llm: hamrpass\n        url: https://codehamr.com\n        key: hp_...\n```\n\n`/models` lists profiles, `/models \u003cname\u003e` switches.\n\n## Hardware\n\nLocal LLMs finally caught up, and we love it. For the best experience we recommend the **~30B class** like **qwen3.6:27b** on **32 GB+ unified RAM / VRAM**, fully local and a real alternative to expensive cloud subscriptions.\n\nInfo for Ollama users: Ollama Desktop may silently cut context to 4k. Open settings and lift the **Context length** slider to **64k+**, depending on your RAM / VRAM.\n\n## Compare\n\n| Tool | Pick if |\n|---|---|\n| **Frontier** | you want commercial heavyweight polish from Claude Code or Codex and accept the subscription cost and session timeouts |\n| **[opencode](https://github.com/anomalyco/opencode)** | you want a great, loaded Swiss army knife and embrace plugin complexity |\n| **[pi-agent](https://github.com/badlogic/pi-mono)** | you want something lighter than opencode and accept configuring your own extensions, skills, and themes |\n| **codehamr** | you want the lightest take on simplicity over complexity and accept no plugins, skills, or sub-agents |\n\n## HamrPass\n\nWe love local LLMs and always will. Codehamr is built fully open\nsource with an MIT license and always will be. Connect to your\nlocal Ollama models, or bring your own key with OpenRouter, OpenAI,\nwhatever you like.\n\nHamrPass is an optional alternative. It's there if you want to\nsupport the project, or if you'd rather not spend your weekend\nbenchmarking the latest open weight model and tuning every\nparameter. We do that work and ship it as one endpoint with sensible\ndefaults, so you can just hamr code and get your shit done.\n\nThere's a waitlist at [codehamr.com](https://codehamr.com). HamrPass only gets built if real demand shows up there. Otherwise it doesn't. Local-first stays the focus.\n\n## License\n\n[MIT](LICENSE). Do whatever you want with it. Star it if it earned one.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcodehamr%2Fcodehamr","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcodehamr%2Fcodehamr","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcodehamr%2Fcodehamr/lists"}