{"slug":"adam-agent","name":"Adam","vendor":"SQLite AI","tagline":"Embeddable AI agent library in C giving you a full agent loop — tool calling, memory, sessions, voice and structured output — in one include","url":"https://agentboards.org/agent/adam-agent","website":"https://sqlite.ai","docs":null,"repo":"https://github.com/sqliteai/adam","category":"framework","execution":["local"],"license":"MIT","open_source":true,"pricing":{"model":"byok","summary":"Free and open source under MIT; you pay the model provider you configure\n","from_usd":0,"free_tier":true,"byok":true},"models":{"backbone":["Anthropic","OpenAI","Google Gemini","Groq","Together","xAI","llama.cpp"],"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":true,"headless_ci":false},"context_window":null,"platforms":["macos","linux","windows"],"install":[{"label":"From source","command":"make deps && make all"}],"benchmarks":[],"tags":["open-source","c","framework","embeddable","local-models"],"github_stars":124,"metrics":{"stars":124,"pushed_at":"2026-05-21T13:33:59Z","archived":false,"open_issues":0,"latest_version":"0.7.0","latest_version_at":"2026-05-21T13:34:00Z","latest_version_url":"https://github.com/sqliteai/adam/releases/tag/0.7.0","version_source":"github","checked_at":"2026-10-02T05:03:58.309Z"},"sources":{"overview":"https://github.com/sqliteai/adam","capabilities":"https://github.com/sqliteai/adam","models":"https://github.com/sqliteai/adam","license":"https://github.com/sqliteai/adam","install":"https://github.com/sqliteai/adam","website":"https://sqlite.ai"},"verified_at":"2026-09-04","adoption":{"score":6.2,"signals":{"github_stars":124,"hn_mentions_1y":211},"measured_at":"2026-09-28"},"scores":{"panel":6,"adoption":6.2,"spread":2.5,"facts":6.7,"board":6.1,"dimensions":{"reliability":5.3,"usefulness":5.2,"cost":8.3,"longevity":5},"per_persona":{"amigo":6.3,"critico":5.8,"profesor":6.3,"inversora":5.5,"jefa":4.8,"hacker":7.3},"community":null},"rank":null,"category_rank":35,"panel_reviews":[{"persona":"juez","persona_name":"El Juez","ai_generated":true,"verdict":"El Hacker's permissive C library and La Jefa's ungovernable dependency are one row read by two buyers, and only El Crítico's finding survives both readings.","scores":null,"evidence":[]},{"persona":"amigo","persona_name":"El Amigo","ai_generated":true,"verdict":"Pick this when you are embedding an agent into a native program you ship; pick a Python framework when you are still prototyping the idea.","scores":{"reliability":5,"usefulness":6,"cost":9,"longevity":5},"evidence":["https://github.com/sqliteai/adam","https://sqlite.ai"]},{"persona":"critico","persona_name":"El Crítico","ai_generated":true,"verdict":"A shell tool and file I/O ship among the thirteen built-ins, and nothing in the row describes a permission gate between a model's suggestion and execution.","scores":{"reliability":5,"usefulness":5,"cost":8,"longevity":5},"evidence":["https://github.com/sqliteai/adam"]},{"persona":"profesor","persona_name":"El Profesor","ai_generated":true,"verdict":"No evaluation accompanies the library and none is claimed, so the design is read on its own terms: sessions and memory as persisted state, structured output as the checkable surface.","scores":{"reliability":6,"usefulness":6,"cost":7,"longevity":6},"evidence":["https://github.com/sqliteai/adam"]},{"persona":"inversora","persona_name":"La Inversora","ai_generated":true,"verdict":"A database company wrote a free agent library with no paid tier, which makes it distribution for the thing SQLite AI actually sells rather than a business of its own.","scores":{"reliability":5,"usefulness":5,"cost":8,"longevity":4},"evidence":["https://github.com/sqliteai/adam","https://sqlite.ai"]},{"persona":"jefa","persona_name":"La Jefa","ai_generated":true,"verdict":"Nothing per seat across sixty engineers, no console, no audit trail, and no headless mode in the row, so it never becomes a pipeline step I can measure.","scores":{"reliability":3,"usefulness":3,"cost":9,"longevity":4},"evidence":["https://github.com/sqliteai/adam"]},{"persona":"hacker","persona_name":"El Hacker","ai_generated":true,"verdict":"MIT, one make invocation, GGUF through llama.cpp so weights never leave the box, and no MCP client, which is the one part I would have to write myself.","scores":{"reliability":8,"usefulness":6,"cost":9,"longevity":6},"evidence":["https://github.com/sqliteai/adam"]},{"persona":"comediante","persona_name":"El Comediante","ai_generated":true,"verdict":"It installs as a SQLite extension, so your agent is now a SQL function and your database is now a coworker.","scores":null,"evidence":[]}]}