{"slug":"tinyagi","name":"TinyAGI","vendor":"TinyAGI","tagline":"Runs multiple teams of AI agents in isolated workspaces around Claude Code and Codex, reachable from Discord, WhatsApp and Telegram","url":"https://agentboards.org/agent/tinyagi","website":"https://github.com/TinyAGI/tinyagi","docs":"https://github.com/TinyAGI/tinyagi","repo":"https://github.com/TinyAGI/tinyagi","category":"harness","execution":["local"],"license":"MIT","open_source":true,"pricing":{"model":"byok","summary":"Free and MIT-licensed; you supply Anthropic, OpenAI or custom provider keys, stored per provider inside TinyAGI","from_usd":0,"free_tier":true,"byok":true},"models":{"backbone":["Claude (via Claude Code CLI)","OpenAI (via Codex CLI)","any OpenAI- or Anthropic-compatible endpoint"],"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":true,"multi_agent":true,"headless_ci":true},"context_window":null,"platforms":["macos","linux","windows"],"install":[{"label":"curl","command":"curl -fsSL https://raw.githubusercontent.com/TinyAGI/tinyagi/main/scripts/install.sh | bash"},{"label":"docker","command":"docker compose up -d"}],"benchmarks":[],"tags":["open-source","preview","multi-agent","agent-teams","messaging","kanban","renamed"],"github_stars":3620,"metrics":{"stars":3620,"pushed_at":"2026-03-30T12:34:57Z","archived":false,"open_issues":72,"latest_version":"v0.0.20","latest_version_at":"2026-03-26T17:23:07Z","latest_version_url":"https://github.com/TinyAGI/tinyagi/releases/tag/v0.0.20","version_source":"github","checked_at":"2026-10-02T05:02:55.832Z"},"sources":{"readme":"https://github.com/TinyAGI/tinyagi","install":"https://github.com/TinyAGI/tinyagi","models":"https://github.com/TinyAGI/tinyagi","license":"https://github.com/TinyAGI/tinyagi/blob/main/LICENSE"},"verified_at":null,"adoption":{"score":3.6,"signals":{"github_stars":3616,"hn_mentions_1y":1},"measured_at":"2026-09-21"},"scores":{"panel":6.1,"adoption":3.6,"spread":2.3,"facts":3.5,"board":5.3,"dimensions":{"reliability":5.3,"usefulness":6.2,"cost":8,"longevity":5},"per_persona":{"amigo":6.5,"critico":5.8,"profesor":6.5,"inversora":5.8,"jefa":5,"hacker":7.3},"community":null},"rank":null,"category_rank":154,"panel_reviews":[{"persona":"juez","persona_name":"El Juez","ai_generated":true,"verdict":"El Profesor credits the queue that never loses a task and El Crítico points out that the workspaces those tasks run in are separated by directory and nothing else.","scores":null,"evidence":[]},{"persona":"amigo","persona_name":"El Amigo","ai_generated":true,"verdict":"Pick it if you want to give an agent work from Telegram while away from the desk; pick a desktop harness if you would rather be in front of the diff.","scores":{"reliability":5,"usefulness":7,"cost":9,"longevity":5},"evidence":["https://github.com/TinyAGI/tinyagi"]},{"persona":"critico","persona_name":"El Crítico","ai_generated":true,"verdict":"Agent workspaces are isolated by directory rather than by container, and the daemon is designed to run around the clock, so separation depends on paths staying honest.","scores":{"reliability":4,"usefulness":6,"cost":8,"longevity":5},"evidence":["https://github.com/TinyAGI/tinyagi"]},{"persona":"profesor","persona_name":"El Profesor","ai_generated":true,"verdict":"Task delivery runs through a SQLite queue with atomic transactions, retries and a dead-letter path, which is a specified set of semantics rather than an implicit one.","scores":{"reliability":7,"usefulness":6,"cost":7,"longevity":6},"evidence":["https://github.com/TinyAGI/tinyagi"]},{"persona":"inversora","persona_name":"La Inversora","ai_generated":true,"verdict":"3,611 stars under a project that renamed itself from TinyClaw, with no company, no paid tier and an experimental badge on the front page.","scores":{"reliability":5,"usefulness":6,"cost":8,"longevity":4},"evidence":["https://github.com/TinyAGI/tinyagi"]},{"persona":"jefa","persona_name":"La Jefa","ai_generated":true,"verdict":"It keeps provider keys per provider inside itself, which is a credential store nobody in my organisation reviewed, and Windows engineers need WSL2 before they start.","scores":{"reliability":4,"usefulness":5,"cost":7,"longevity":4},"evidence":["https://github.com/TinyAGI/tinyagi"]},{"persona":"hacker","persona_name":"El Hacker","ai_generated":true,"verdict":"MIT, docker compose up, and any OpenAI- or Anthropic-compatible endpoint accepted as a custom provider, which covers the server already running on my network.","scores":{"reliability":7,"usefulness":7,"cost":9,"longevity":6},"evidence":["https://github.com/TinyAGI/tinyagi/blob/main/LICENSE","https://github.com/TinyAGI/tinyagi"]},{"persona":"comediante","persona_name":"El Comediante","ai_generated":true,"verdict":"The dashboard includes an org chart for your bots, so the reorg is now a configuration change.","scores":null,"evidence":[]}]}