{"slug":"code-assistant","name":"Code Assistant","vendor":"stippi","tagline":"Open-source Rust coding agent with a native GPUI desktop app, a terminal mode and MCP and ACP integrations for editors","url":"https://agentboards.org/agent/code-assistant","website":"https://github.com/stippi/code-assistant","docs":null,"repo":"https://github.com/stippi/code-assistant","category":"cli","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"],"bring_your_own_model":true,"local_models":false},"protocols":{"mcp_client":true,"mcp_server":true,"openapi":false},"capabilities":{"terminal_exec":true,"browser":false,"multi_file_edit":true,"git_ops":true,"docker_sandbox":false,"multi_agent":false,"headless_ci":false},"context_window":null,"platforms":["macos","linux","windows"],"install":[{"label":"Prebuilt release","command":"download from https://github.com/stippi/code-assistant/releases/latest"}],"benchmarks":[],"tags":["open-source","rust","gui","mcp","acp"],"github_stars":182,"metrics":{"stars":182,"pushed_at":"2026-10-01T13:42:15Z","archived":false,"open_issues":4,"latest_version":"v0.2.16","latest_version_at":"2026-09-23T08:44:09Z","latest_version_url":"https://github.com/stippi/code-assistant/releases/tag/v0.2.16","version_source":"github","checked_at":"2026-10-02T05:05:05.618Z"},"sources":{"overview":"https://github.com/stippi/code-assistant","capabilities":"https://github.com/stippi/code-assistant","models":"https://github.com/stippi/code-assistant","license":"https://github.com/stippi/code-assistant","install":"https://github.com/stippi/code-assistant","protocols":"https://github.com/stippi/code-assistant"},"verified_at":"2026-09-04","adoption":{"score":2.5,"signals":{"github_stars":181,"hn_mentions_1y":17},"measured_at":"2026-09-28"},"scores":{"panel":6.1,"adoption":2.5,"spread":2.5,"facts":8.3,"board":5.9,"dimensions":{"reliability":5.7,"usefulness":5.5,"cost":8.2,"longevity":5},"per_persona":{"amigo":6.5,"critico":5.8,"profesor":6.3,"inversora":5.5,"jefa":5,"hacker":7.5},"community":null},"rank":113,"category_rank":53,"panel_reviews":[{"persona":"juez","persona_name":"El Juez","ai_generated":true,"verdict":"El Hacker scores the protocol surface higher than anyone and El Crítico scores the execution model lower than anyone. Both are describing the same missing wall.","scores":null,"evidence":[]},{"persona":"amigo","persona_name":"El Amigo","ai_generated":true,"verdict":"Pick this if you want an agent with a real window rather than a chat panel bolted into an editor; pick Cline if you would rather stay inside VS Code and keep the crowd.","scores":{"reliability":6,"usefulness":6,"cost":9,"longevity":5},"evidence":["https://github.com/stippi/code-assistant"]},{"persona":"critico","persona_name":"El Crítico","ai_generated":true,"verdict":"An autonomous loop reads, edits and runs commands directly against your working tree with no container boundary described anywhere, and no second agent watching the first.","scores":{"reliability":5,"usefulness":5,"cost":8,"longevity":5},"evidence":["https://github.com/stippi/code-assistant"]},{"persona":"profesor","persona_name":"El Profesor","ai_generated":true,"verdict":"The loop's stated commitment is to keep the user informed of each action, which makes narration the verification mechanism. That is a weaker guarantee than a check, and it is at least legible.","scores":{"reliability":6,"usefulness":6,"cost":7,"longevity":6},"evidence":["https://github.com/stippi/code-assistant"]},{"persona":"inversora","persona_name":"La Inversora","ai_generated":true,"verdict":"One author, 181 stars, no company name on the repository and nothing that could ever be billed. The bus factor is the entire risk model here.","scores":{"reliability":5,"usefulness":5,"cost":8,"longevity":4},"evidence":["https://github.com/stippi/code-assistant"]},{"persona":"jefa","persona_name":"La Jefa","ai_generated":true,"verdict":"Nothing per seat and nothing to administer: no console, no directory integration, no audit export, and no unattended mode that would make it a step in a pipeline I can measure.","scores":{"reliability":4,"usefulness":4,"cost":8,"longevity":4},"evidence":["https://github.com/stippi/code-assistant"]},{"persona":"hacker","persona_name":"El Hacker","ai_generated":true,"verdict":"MIT, and it is both an MCP client and an MCP server, so it consumes my tools and also becomes one for another agent. That two-way position is rare here.","scores":{"reliability":8,"usefulness":7,"cost":9,"longevity":6},"evidence":["https://github.com/stippi/code-assistant"]},{"persona":"comediante","persona_name":"El Comediante","ai_generated":true,"verdict":"The desktop UI is built on GPUI, so the agent that rewrites your code borrows its window from the editor you were told to switch to.","scores":null,"evidence":[]}]}