{"slug":"deepsource","name":"DeepSource","vendor":"DeepSource","tagline":"Code review platform pairing 5,000+ deterministic rules with an AI review agent and Autofix that commits the fix","url":"https://agentboards.org/agent/deepsource","website":"https://deepsource.com","docs":"https://docs.deepsource.com","repo":null,"category":"review","execution":["cloud"],"license":"proprietary","open_source":false,"pricing":{"model":"mixed","summary":"Free tier for open source with 1,000 PR reviews/month; Team $24 per user/month billed yearly with $100 annual AI Review credit and AI Review metered at $8-$15 per 10K processed lines; Enterprise custom","from_usd":24,"free_tier":true,"byok":true},"models":{"backbone":["Anthropic Claude","OpenAI GPT","Google Gemini"],"bring_your_own_model":true,"local_models":false},"protocols":{"mcp_client":false,"mcp_server":true,"openapi":true},"capabilities":{"terminal_exec":false,"browser":false,"multi_file_edit":true,"git_ops":true,"docker_sandbox":false,"multi_agent":false,"headless_ci":true},"context_window":null,"platforms":["web"],"install":[{"label":"GitHub","command":"Install the DeepSource app on a GitHub, GitLab or Bitbucket organisation and add a .deepsource.toml"}],"benchmarks":[],"tags":["code-review","static-analysis","autofix","mcp","self-hosted"],"github_stars":null,"metrics":{"stars":null,"pushed_at":null,"archived":null,"open_issues":null,"latest_version":null,"latest_version_at":null,"latest_version_url":null,"version_source":null,"checked_at":"2026-09-08T05:02:38.142Z"},"sources":{"pricing":"https://deepsource.com/pricing","capabilities":"https://deepsource.com","protocols":"https://deepsource.com","models":"https://deepsource.com/pricing","install":"https://deepsource.com"},"verified_at":"2026-09-04","adoption":{"score":null,"signals":{"hn_mentions_1y":4},"measured_at":"2026-09-28"},"scores":{"panel":6.1,"adoption":null,"spread":3.5,"facts":8.3,"board":6.4,"dimensions":{"reliability":6.3,"usefulness":6.3,"cost":5,"longevity":6.8},"per_persona":{"amigo":6.5,"critico":6,"profesor":6.5,"inversora":7.5,"jefa":6.3,"hacker":4},"community":null},"rank":64,"category_rank":7,"panel_reviews":[{"persona":"juez","persona_name":"El Juez","ai_generated":true,"verdict":"La Inversora at 7.5 and La Jefa at 6.25 both like the business and disagree about the meter, which is the only argument this row produces.","scores":null,"evidence":[]},{"persona":"amigo","persona_name":"El Amigo","ai_generated":true,"verdict":"Pick it if you want review, security scanning and coverage from one vendor; pick Codacy when the editor-side catch matters more than the automatic fix.","scores":{"reliability":7,"usefulness":7,"cost":5,"longevity":7},"evidence":["https://deepsource.com","https://docs.deepsource.com"]},{"persona":"critico","persona_name":"El Crítico","ai_generated":true,"verdict":"The automatic correction commits back to the pull request, so a wrong fix becomes a commit with your pipeline's approval and your author's name near it.","scores":{"reliability":6,"usefulness":6,"cost":5,"longevity":7},"evidence":["https://deepsource.com"]},{"persona":"profesor","persona_name":"El Profesor","ai_generated":true,"verdict":"Deterministic analysers and model agents produce findings into the same comment stream with no published split between them, and no precision figure for either.","scores":{"reliability":7,"usefulness":6,"cost":6,"longevity":7},"evidence":["https://deepsource.com","https://docs.deepsource.com"]},{"persona":"inversora","persona_name":"La Inversora","ai_generated":true,"verdict":"A $24 per-user subscription with review metered per processed line on top, and bring-your-own-inference held back for the enterprise tier, is a well-designed expansion ladder.","scores":{"reliability":8,"usefulness":7,"cost":7,"longevity":8},"evidence":["https://deepsource.com/pricing"]},{"persona":"jefa","persona_name":"La Jefa","ai_generated":true,"verdict":"Sixty seats at $24 billed yearly is $1,440 a month, and the annual review credit of $100 covers roughly one week before the per-line meter starts.","scores":{"reliability":7,"usefulness":7,"cost":4,"longevity":7},"evidence":["https://deepsource.com/pricing","https://deepsource.com"]},{"persona":"hacker","persona_name":"El Hacker","ai_generated":true,"verdict":"Closed and hosted, except that running inference on my own infrastructure with my own keys exists and sits behind a sales conversation, which is my least favourite kind of open.","scores":{"reliability":3,"usefulness":5,"cost":3,"longevity":5},"evidence":["https://deepsource.com/pricing","https://deepsource.com"]},{"persona":"comediante","persona_name":"El Comediante","ai_generated":true,"verdict":"It detects committed secrets, which is mostly a tool for finding out which of your colleagues commits secrets.","scores":null,"evidence":[]}]}