{"id":50390848,"url":"https://github.com/lexus2016/consilium","last_synced_at":"2026-05-30T18:00:33.178Z","repository":{"id":360930697,"uuid":"1252324035","full_name":"Lexus2016/consilium","owner":"Lexus2016","description":"Cross-agent consultation bus for AI coding CLIs — ask one agent for a second opinion from inside another (Claude Code, Antigravity, OpenCode, Codex).","archived":false,"fork":false,"pushed_at":"2026-05-28T13:55:38.000Z","size":41,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-28T14:10:58.250Z","etag":null,"topics":["agentic","ai","ai-agents","antigravity","bash","claude-code","cli","code-review","codex","developer-tools","llm","opencode"],"latest_commit_sha":null,"homepage":null,"language":"PowerShell","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Lexus2016.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-05-28T12:06:10.000Z","updated_at":"2026-05-28T13:53:26.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/Lexus2016/consilium","commit_stats":null,"previous_names":["lexus2016/consilium"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/Lexus2016/consilium","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lexus2016%2Fconsilium","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lexus2016%2Fconsilium/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lexus2016%2Fconsilium/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lexus2016%2Fconsilium/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Lexus2016","download_url":"https://codeload.github.com/Lexus2016/consilium/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lexus2016%2Fconsilium/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33703065,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-05-30T02:00:06.278Z","response_time":92,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agentic","ai","ai-agents","antigravity","bash","claude-code","cli","code-review","codex","developer-tools","llm","opencode"],"created_at":"2026-05-30T18:00:30.892Z","updated_at":"2026-05-30T18:00:33.166Z","avatar_url":"https://github.com/Lexus2016.png","language":"PowerShell","funding_links":[],"categories":[],"sub_categories":[],"readme":"# consilium\n\n**English** · [Українська](README.uk.md) · [Русский](README.ru.md)\n\n\u003e Let your AI ask a different AI when it isn't sure.\n\nYour coding assistant is good, but it has the same problem the rest of us do: it\ncan't always tell when it's wrong. It will convince itself a migration is safe,\nmiss a race condition, or keep hammering a broken approach long after it should\nhave stopped. consilium gives it an out: it hands the same code to a different\nmodel (Claude, GPT, or Gemini) and asks what that one thinks. The other AI only\nanswers. It never changes your files.\n\n\u003e Still early, but I reach for it most days.\n\n## When it's worth asking\n\nA second read pays off in moments like these.\n\nYou're about to run a database migration and you're not sure it's safe if it runs\ntwice. Ask before you hit enter, not after.\n\nA retry loop passes every test and still falls over in production once a day.\nAnother model reads the back-off logic and spots the off-by-one you'd stopped\nnoticing.\n\nYou and your assistant have spent an hour on one bug, each fix breaking the last.\nTime to bring in a model that wasn't there for the first fifty-nine minutes.\n\nThe auth check looks right. But you wrote it, so of course it does. Send it to a\ndifferent model and ask the one question that counts: can this be bypassed?\n\nRelease is minutes away and something about backwards compatibility nags at you,\nthough you can't name it yet. Two minutes now is cheaper than a rollback at\nmidnight.\n\n## Install it (just ask your AI)\n\nPaste this to your assistant (Claude Code, Codex, OpenCode, or Antigravity):\n\n\u003e Install consilium from https://github.com/Lexus2016/consilium for me: clone it,\n\u003e run its `install.sh`, and set yourself up to ask other AIs for a second opinion\n\u003e the way its `clients/README.md` describes.\n\nThat's it. You only need the assistants you actually plan to ask.\n\n## Update it\n\nFrom your consilium clone, one command pulls the latest and re-syncs everything:\n\n    git pull \u0026\u0026 ./install.sh --clients\n\nThe CLI is symlinked, so the `consult` command tracks `git pull` on its own;\n`--clients` refreshes the hub block in the agents you use (codex/opencode/agy)\nand the Claude skill. The hub block carries no agent list, so new advisors never\nneed a manual re-sync.\n\n## Use it\n\nJust say what you want, in plain words:\n\n\u003e \"Before we continue, get a second opinion from codex on this.\"\n\n\u003e \"Ask another AI whether this change is safe.\"\n\n\u003e \"I'm stuck. Check this with agy.\"\n\nIt runs the request, shows you the reply, and tells you whether it agrees. What\nhappens next is your call.\n\nIf you'd rather run it yourself, it's one line: who you're asking, then the\nquestion.\n\n```\nconsult codex -- \"Is it safe to do it this way?\"\n```\n\n## Good to know\n\n- The other AI advises, it doesn't act. consilium won't let it skip safety checks,\n  and it answers without editing your files.\n- The assistants you want to ask have to be installed and signed in first. Run\n  `consult --list` to see who's ready.\n- It runs in your current project folder, so your code is already in front of it.\n- Ask a different model than the one you're using. A second Claude mostly agrees\n  with the first.\n- Every call is a real request to another model, so save it for the things that\n  matter.\n- Don't put passwords or keys in the question.\n\n## Read more\n\n- Real situations, in plain language: [`docs/examples.md`](docs/examples.md)\n- A short guide for you: [`docs/usage.md`](docs/usage.md)\n- The playbook your assistant follows: [`docs/consulting-guide.md`](docs/consulting-guide.md)\n- How it's built, if you're curious: [`docs/architecture.md`](docs/architecture.md)\n\n## License\n\n[MIT](LICENSE)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flexus2016%2Fconsilium","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flexus2016%2Fconsilium","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flexus2016%2Fconsilium/lists"}