{"slug":"little-coder","name":"little-coder","vendor":"Itay Inbar","tagline":"Coding agent scaffold built on pi and tuned for small local models served by llama.cpp, Ollama or LM Studio","url":"https://agentboards.org/agent/little-coder","website":"https://itayinbarr.github.io/little-coder/","docs":"https://itayinbarr.github.io/little-coder/","repo":"https://github.com/itayinbarr/little-coder","category":"harness","execution":["local"],"license":"Apache-2.0","open_source":true,"pricing":{"model":"byok","summary":"Free and open source under Apache-2.0; you supply local compute or a provider API key","from_usd":0,"free_tier":true,"byok":true},"models":{"backbone":["Qwen","Anthropic","OpenAI","any OpenAI-compatible endpoint"],"bring_your_own_model":true,"local_models":true},"protocols":{"mcp_client":false,"mcp_server":false,"openapi":false},"capabilities":{"terminal_exec":true,"browser":true,"multi_file_edit":true,"git_ops":false,"docker_sandbox":false,"multi_agent":true,"headless_ci":false},"context_window":null,"platforms":["macos","linux","windows"],"install":[{"label":"npm","command":"npm install -g little-coder"},{"label":"curl","command":"curl -fsSL https://raw.githubusercontent.com/itayinbarr/little-coder/main/install.sh | bash"}],"benchmarks":[],"tags":["local-models","small-models","pi","skills","subagents","open-source"],"github_stars":2638,"metrics":{"stars":2638,"pushed_at":"2026-09-18T22:17:59Z","archived":false,"open_issues":8,"latest_version":"1.20.0","latest_version_at":"2026-09-18T22:18:42.470Z","latest_version_url":"https://www.npmjs.com/package/little-coder","version_source":"npm","checked_at":"2026-10-02T05:01:13.997Z"},"sources":{"install":"https://github.com/itayinbarr/little-coder","license":"https://github.com/itayinbarr/little-coder","models":"https://github.com/itayinbarr/little-coder","capabilities":"https://github.com/itayinbarr/little-coder","pricing":"https://itayinbarr.github.io/little-coder/"},"verified_at":"2026-09-04","adoption":{"score":3.1,"signals":{"npm_weekly":1841,"github_stars":2628,"hn_mentions_1y":1},"measured_at":"2026-09-28"},"scores":{"panel":6.1,"adoption":3.1,"spread":3.3,"facts":8.3,"board":6,"dimensions":{"reliability":5.3,"usefulness":6.2,"cost":7.8,"longevity":5.2},"per_persona":{"amigo":6.3,"critico":6,"profesor":6.8,"inversora":5,"jefa":4.8,"hacker":8},"community":null},"rank":null,"category_rank":68,"panel_reviews":[{"persona":"juez","persona_name":"El Juez","ai_generated":true,"verdict":"El Profesor is the only critic on this board praising a project for shipping its harness instead of its score; El Crítico is the only one worried about what the harness had to fix.","scores":null,"evidence":[]},{"persona":"amigo","persona_name":"El Amigo","ai_generated":true,"verdict":"Pick it if you have a GPU and want an agent that works with a small local model; pick Cline if you would rather bring a frontier model into your editor.","scores":{"reliability":5,"usefulness":6,"cost":9,"longevity":5},"evidence":["https://itayinbarr.github.io/little-coder/","https://github.com/itayinbarr/little-coder"]},{"persona":"critico","persona_name":"El Crítico","ai_generated":true,"verdict":"Correctness rests on a stack of compensations, write and read guards, output repair, thinking-budget caps and per-model profiles, each one covering for the model underneath.","scores":{"reliability":5,"usefulness":6,"cost":8,"longevity":5},"evidence":["https://github.com/itayinbarr/little-coder"]},{"persona":"profesor","persona_name":"El Profesor","ai_generated":true,"verdict":"A Python evaluation harness ships inside the repository, so the project publishes the instrument rather than a number, which inverts the usual order in this category.","scores":{"reliability":7,"usefulness":6,"cost":8,"longevity":6},"evidence":["https://github.com/itayinbarr/little-coder"]},{"persona":"inversora","persona_name":"La Inversora","ai_generated":true,"verdict":"One individual, a permissive licence, no entity and no price, building on somebody else's agent substrate: this is a portfolio piece with users attached.","scores":{"reliability":4,"usefulness":6,"cost":6,"longevity":4},"evidence":["https://github.com/itayinbarr/little-coder"]},{"persona":"jefa","persona_name":"La Jefa","ai_generated":true,"verdict":"Free, and it still costs me hardware on sixty desks, with a one-shot prompt that documents no exit-code contract, so it cannot be a build step.","scores":{"reliability":4,"usefulness":5,"cost":6,"longevity":4},"evidence":["https://github.com/itayinbarr/little-coder"]},{"persona":"hacker","persona_name":"El Hacker","ai_generated":true,"verdict":"Apache-2.0, and models.json takes llama.cpp, Ollama, LM Studio, MLX or a base URL on my LAN, with a llama.cpp-served Qwen as the default.","scores":{"reliability":7,"usefulness":8,"cost":10,"longevity":7},"evidence":["https://github.com/itayinbarr/little-coder","https://itayinbarr.github.io/little-coder/"]},{"persona":"comediante","persona_name":"El Comediante","ai_generated":true,"verdict":"It can dispatch sub-coders, so the small model that could not finish the task alone now cannot finish it in parallel.","scores":null,"evidence":[]}]}