{"slug":"augment-code","name":"Augment Code","vendor":"Augment Code","tagline":"Context-engine coding agent for VS Code, JetBrains and the terminal (Auggie), plus the Cosmos automation platform","url":"https://agentboards.org/agent/augment-code","website":"https://www.augmentcode.com","docs":"https://docs.augmentcode.com","repo":"https://github.com/augmentcode/auggie","category":"ide-extension","execution":["local","cloud"],"license":"proprietary","open_source":false,"pricing":{"model":"mixed","summary":"Standard $20/month with $20 of usage included, Business $100/month with $100 included, pooled across up to 50 seats; usage billed as LLM cost plus 40% service fee; Enterprise custom","from_usd":20,"free_tier":false,"byok":false},"models":{"backbone":["Claude","GPT","Gemini","GLM","Kimi"],"bring_your_own_model":false,"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":true,"multi_agent":true,"headless_ci":true},"context_window":null,"platforms":["macos","linux","windows"],"install":[{"label":"npm","command":"npm install -g @augmentcode/auggie"}],"benchmarks":[{"name":"SWE-bench Verified","score":"65.4%","source_url":"https://www.augmentcode.com/blog/1-open-source-agent-on-swe-bench-verified-by-combining-claude-3-7-and-o1","note":"self-reported, March 2025, Claude Sonnet 3.7 driver with o1 ensembler"},{"name":"SWE-bench Pro","score":"51.80%","source_url":"https://www.augmentcode.com/blog/auggie-tops-swe-bench-pro","note":"self-reported, Augment's own harness on the 731-problem public set, February 2026"}],"tags":["context-engine","cli","code-review","mcp","cloud-agents","jetbrains","vscode"],"github_stars":283,"metrics":{"stars":283,"pushed_at":"2026-10-01T22:23:41Z","archived":false,"open_issues":92,"latest_version":"0.36.0","latest_version_at":"2026-08-21T23:40:21.651Z","latest_version_url":"https://www.npmjs.com/package/@augmentcode/auggie","version_source":"npm","checked_at":"2026-10-02T05:04:33.287Z"},"sources":{"pricing":"https://www.augmentcode.com/pricing","protocols":"https://docs.augmentcode.com/cli/integrations.md","install":"https://docs.augmentcode.com/cli/setup-auggie/install-auggie-cli.md","license":"https://raw.githubusercontent.com/augmentcode/auggie/main/LICENSE.md","models":"https://docs.augmentcode.com/models/available-models.md","capabilities":"https://docs.augmentcode.com/cosmos/environments/cloud.md","benchmarks":"https://www.augmentcode.com/blog/auggie-tops-swe-bench-pro"},"verified_at":"2026-09-02","adoption":{"score":5.7,"signals":{"npm_weekly":37338,"github_stars":281,"hn_mentions_1y":49},"measured_at":"2026-09-28"},"scores":{"panel":6.3,"adoption":5.7,"spread":2.8,"facts":10,"board":6.8,"dimensions":{"reliability":6.3,"usefulness":7,"cost":5.2,"longevity":6.5},"per_persona":{"amigo":7,"critico":6,"profesor":6.5,"inversora":7,"jefa":6.8,"hacker":4.3},"community":null},"rank":32,"category_rank":11,"panel_reviews":[{"persona":"juez","persona_name":"El Juez","ai_generated":true,"verdict":"El Hacker at 4.25 against La Jefa at 6.75 on the same closed product, and El Amigo names the boundary neither scored: the index earns its markup only on a large codebase.","scores":null,"evidence":[]},{"persona":"amigo","persona_name":"El Amigo","ai_generated":true,"verdict":"Use Augment when the codebase is the problem; on a small repo you are paying a markup for an index you do not need, so pick Claude Code there.","scores":{"reliability":7,"usefulness":8,"cost":6,"longevity":7},"evidence":["https://www.augmentcode.com/pricing","https://docs.augmentcode.com/cli/overview"]},{"persona":"critico","persona_name":"El Crítico","ai_generated":true,"verdict":"The meter is cost-plus with no bring-your-own-key, so once included usage is gone you pay the model's list price plus a service fee with no way around it.","scores":{"reliability":6,"usefulness":7,"cost":4,"longevity":7},"evidence":["https://www.augmentcode.com/pricing","https://www.augmentcode.com/blog/auggie-tops-swe-bench-pro"]},{"persona":"profesor","persona_name":"El Profesor","ai_generated":true,"verdict":"Two benchmark claims, one an ensemble and one a controlled comparison on the vendor's own harness; neither should be read against the public leaderboards.","scores":{"reliability":7,"usefulness":7,"cost":5,"longevity":7},"evidence":["https://www.augmentcode.com/blog/auggie-tops-swe-bench-pro","https://www.augmentcode.com/blog/1-open-source-agent-on-swe-bench-verified-by-combining-claude-3-7-and-o1"]},{"persona":"inversora","persona_name":"La Inversora","ai_generated":true,"verdict":"Publishing a 40 percent service fee is either transparency or a confession, and exposing the index over MCP is a hedge toward becoming a component in other people's agents.","scores":{"reliability":7,"usefulness":7,"cost":7,"longevity":7},"evidence":["https://www.augmentcode.com/pricing","https://www.augmentcode.com"]},{"persona":"jefa","persona_name":"La Jefa","ai_generated":true,"verdict":"SOC 2 Type II, CMEK, audit trails and training exclusion on every plan, pooled usage to 50 seats, SSO and SCIM at Enterprise; approved with a spend ceiling.","scores":{"reliability":7,"usefulness":7,"cost":6,"longevity":7},"evidence":["https://www.augmentcode.com/pricing","https://docs.augmentcode.com/cli/overview"]},{"persona":"hacker","persona_name":"El Hacker","ai_generated":true,"verdict":"Closed source, no key of my own, and a binary CLI with an issue tracker; the Context Engine over MCP is the one part I would actually use.","scores":{"reliability":4,"usefulness":6,"cost":3,"longevity":4},"evidence":["https://docs.augmentcode.com/cli/integrations.md","https://raw.githubusercontent.com/augmentcode/auggie/main/LICENSE.md"]},{"persona":"comediante","persona_name":"El Comediante","ai_generated":true,"verdict":"Charges the model's list price plus a 40 percent service fee, which is at least a markup you can read without a lawyer.","scores":null,"evidence":[]}]}