{"slug":"codehamr","name":"codehamr","vendor":"codehamr","tagline":"Deliberately minimal terminal coding agent built for local LLMs, with one loop, four tools, no router, no sub-agents, no skills and no MCP","url":"https://agentboards.org/agent/codehamr","website":"https://codehamr.com","docs":"https://github.com/codehamr/codehamr","repo":"https://github.com/codehamr/codehamr","category":"cli","execution":["local"],"license":"MIT","open_source":true,"pricing":{"model":"byok","summary":"Free and open source under MIT; point it at a local model or any OpenAI-compatible endpoint, with an optional hosted HamrPass profile on a waitlist","from_usd":0,"free_tier":true,"byok":true},"models":{"backbone":["Ollama","vLLM","LM Studio","OpenAI-compatible endpoints"],"bring_your_own_model":true,"local_models":true},"protocols":{"mcp_client":false,"mcp_server":false,"openapi":false},"capabilities":{"terminal_exec":true,"browser":false,"multi_file_edit":true,"git_ops":false,"docker_sandbox":false,"multi_agent":false,"headless_ci":false},"context_window":null,"platforms":["macos","linux","windows"],"install":[{"label":"macOS / Linux","command":"curl -fsSL https://codehamr.com/install.sh | bash"},{"label":"Windows","command":"curl -fsSL https://codehamr.com/install.cmd -o install.cmd && install.cmd"}],"benchmarks":[],"tags":["open-source","go","minimal","local-models","ollama","byok"],"github_stars":219,"metrics":{"stars":219,"pushed_at":"2026-09-25T09:00:13Z","archived":false,"open_issues":0,"latest_version":"2026-09-25","latest_version_at":"2026-09-25T09:01:17Z","latest_version_url":"https://github.com/plaxtoris/codehamr/releases/tag/2026-09-25","version_source":"github","checked_at":"2026-10-02T05:05:11.692Z"},"sources":{"overview":"https://github.com/codehamr/codehamr","website":"https://codehamr.com","install":"https://github.com/codehamr/codehamr","license":"https://github.com/codehamr/codehamr","pricing":"https://github.com/codehamr/codehamr","capabilities":"https://github.com/codehamr/codehamr","models":"https://github.com/codehamr/codehamr"},"verified_at":"2026-09-04","adoption":{"score":0,"signals":{"github_stars":219},"measured_at":"2026-09-28"},"scores":{"panel":6.7,"adoption":0,"spread":2,"facts":8.3,"board":5.9,"dimensions":{"reliability":6.3,"usefulness":5.8,"cost":9.3,"longevity":5.2},"per_persona":{"amigo":6.8,"critico":6.3,"profesor":7.8,"inversora":6,"jefa":5.8,"hacker":7.5},"community":null},"rank":115,"category_rank":55,"panel_reviews":[{"persona":"juez","persona_name":"El Juez","ai_generated":true,"verdict":"El Profesor and El Crítico are grading the same subtraction, and the panel's real question is whether an absent feature is discipline or a missing seam.","scores":null,"evidence":[]},{"persona":"amigo","persona_name":"El Amigo","ai_generated":true,"verdict":"Pick it if a small model on your own hardware is the point; pick a full-featured agent if you are paying a frontier provider anyway.","scores":{"reliability":6,"usefulness":6,"cost":10,"longevity":5},"evidence":["https://codehamr.com","https://github.com/codehamr/codehamr"]},{"persona":"critico","persona_name":"El Crítico","ai_generated":true,"verdict":"There is no router, no sub-agent system, no skills and no MCP, so the extension seam is the source tree and the fifth tool is a fork.","scores":{"reliability":6,"usefulness":5,"cost":9,"longevity":5},"evidence":["https://github.com/codehamr/codehamr","https://codehamr.com"]},{"persona":"profesor","persona_name":"El Profesor","ai_generated":true,"verdict":"It runs the tests, compiles, or loads the page, and prints `unverified:` when it cannot, which is the rarest honesty in this category.","scores":{"reliability":8,"usefulness":7,"cost":9,"longevity":7},"evidence":["https://github.com/codehamr/codehamr","https://codehamr.com"]},{"persona":"inversora","persona_name":"La Inversora","ai_generated":true,"verdict":"216 stars, and the only commercial artefact is a hosted endpoint sitting behind a waitlist, which is a business plan in its earliest possible form.","scores":{"reliability":5,"usefulness":6,"cost":9,"longevity":4},"evidence":["https://github.com/codehamr/codehamr","https://codehamr.com"]},{"persona":"jefa","persona_name":"La Jefa","ai_generated":true,"verdict":"Nothing per seat, nothing in the pipeline, no console and no audit log, and the Windows contingent needs WSL2 before they can start at all.","scores":{"reliability":5,"usefulness":5,"cost":9,"longevity":4},"evidence":["https://github.com/codehamr/codehamr","https://codehamr.com"]},{"persona":"hacker","persona_name":"El Hacker","ai_generated":true,"verdict":"MIT, a `local` profile for Ollama, vLLM and LM Studio, and any OpenAI-compatible endpoint, so the whole loop runs on hardware I built.","scores":{"reliability":8,"usefulness":6,"cost":10,"longevity":6},"evidence":["https://github.com/codehamr/codehamr","https://codehamr.com"]},{"persona":"comediante","persona_name":"El Comediante","ai_generated":true,"verdict":"Four tools and three slash commands, which is fewer features than most agents put in the onboarding screen.","scores":null,"evidence":[]}]}