{"id":49581312,"url":"https://github.com/omeryasirkucuk/amx","last_synced_at":"2026-06-07T22:01:07.126Z","repository":{"id":352497727,"uuid":"1215321844","full_name":"omeryasirkucuk/amx","owner":"omeryasirkucuk","description":"AI-driven CLI for documenting database schemas. DB + docs + codebase agents, 10 backends, BYO LLM, human-in-the-loop review.","archived":false,"fork":false,"pushed_at":"2026-06-07T16:28:51.000Z","size":67261,"stargazers_count":16,"open_issues_count":1,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-07T17:15:37.236Z","etag":null,"topics":["agentic-ai","ai-agents","bigquery","cli","data-catalog","data-engineering","database-documentation","databricks","human-in-the-loop","llm","metadata","postgre","python","snowflake"],"latest_commit_sha":null,"homepage":"https://amxcli.com","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/omeryasirkucuk.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","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":"2026-04-19T19:07:21.000Z","updated_at":"2026-06-07T16:28:52.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/omeryasirkucuk/amx","commit_stats":null,"previous_names":["omeryasirkucuk/amx"],"tags_count":18,"template":false,"template_full_name":null,"purl":"pkg:github/omeryasirkucuk/amx","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/omeryasirkucuk%2Famx","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/omeryasirkucuk%2Famx/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/omeryasirkucuk%2Famx/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/omeryasirkucuk%2Famx/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/omeryasirkucuk","download_url":"https://codeload.github.com/omeryasirkucuk/amx/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/omeryasirkucuk%2Famx/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34039495,"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":"2026-06-07T02:00:07.652Z","response_time":124,"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","bigquery","cli","data-catalog","data-engineering","database-documentation","databricks","human-in-the-loop","llm","metadata","postgre","python","snowflake"],"created_at":"2026-05-03T20:03:38.823Z","updated_at":"2026-06-07T22:01:07.121Z","avatar_url":"https://github.com/omeryasirkucuk.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://raw.githubusercontent.com/omeryasirkucuk/amx/main/docs/assets/amx-readme.gif\" alt=\"AMX in action\" width=\"760\"\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cstrong\u003eCryptic columns, reviewed comments.\u003c/strong\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  AMX walks your database, reads your codebase and docs, then drafts a\n  \u003ccode\u003eCOMMENT\u003c/code\u003e for every table, view, and column — with confidence\n  scores and a human review before anything lands in the live database.\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://amxcli.com/\"\u003e\u003cstrong\u003eDocumentation\u003c/strong\u003e\u003c/a\u003e\n  ·\n  \u003ca href=\"https://amxcli.com/getting-started/quickstart/\"\u003eQuickstart\u003c/a\u003e\n  ·\n  \u003ca href=\"https://github.com/omeryasirkucuk/amx/blob/main/CHANGELOG.md\"\u003eChangelog\u003c/a\u003e\n  ·\n  \u003ca href=\"https://github.com/omeryasirkucuk/amx/issues\"\u003eIssues\u003c/a\u003e\n\u003c/p\u003e\n\n---\n\n_AMX is in early development — expect breaking changes between releases. Stay current with `pip install --upgrade amx-cli`._\n\nThree independent sub-agents — **Profile** (schema, stats, sample values), **RAG** (ingested docs), and **Code** (references mined from your repos) — gather evidence in parallel. An orchestrator merges and ranks them, you accept / edit / skip each suggestion, and AMX writes the approved text back as native `COMMENT` statements on the engine.\n\nFive minutes from `pip install` to your first reviewed comment. **Ten database engines, seven LLM providers.**\n\n## Install\n\n```bash\npip install amx-cli\n```\n\nThe PyPI distribution is `amx-cli`; the import package is `amx` (`import amx`). Requires Python 3.10+. See the [installation guide](https://amxcli.com/getting-started/installation/) for prerequisites, source builds, and where AMX writes config / history / logs.\n\n## Quick start\n\n```bash\namx                       # open the interactive session (the AMX REPL)\n/setup                    # one-time wizard: DB profile + LLM profile\n/connect                  # sanity-check the active connection\n/run sales.orders         # generate suggestions, review, accept\n/apply                    # write approved descriptions back to the database\n```\n\n`/run` without an argument opens a scope picker (Database / Schema / Asset). `/run-apply` short-circuits review-and-apply when you already trust the model. If anything misbehaves, `amx doctor` runs from any shell — even when AMX itself can't start — and prints actionable hints next to each ✗.\n\nThe full guided walkthrough is at the [5-minute quickstart](https://amxcli.com/getting-started/quickstart/) and [first-run walkthrough](https://amxcli.com/getting-started/first-run/).\n\n## AMX CLI\n\nA typical session — running `/run`, inspecting ranked suggestions inline, accepting or editing each one before it lands in the database.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://raw.githubusercontent.com/omeryasirkucuk/amx/main/docs/assets/amx-banner.png\" alt=\"AMX REPL — interactive session showing /run output with ranked suggestions, confidence scores, and review prompts\" width=\"900\"\u003e\n\u003c/p\u003e\n\n## AMX Studio (`/studio`) — same workflow on a local web UI\n\nFrom inside the REPL, `/studio` boots **AMX Studio**, a token-protected web UI on `127.0.0.1`, and opens your browser. Same review-and-apply workflow as the REPL — runs, results, the pending queue, the `/ask` chat, and full DB / LLM / Docs / Code profile management — but on a denser surface. **Browse** any database / schema / table to inline-edit comments or hit per-asset **Generate** to draft just one comment through the same human-in-the-loop queue. The SPA bundle ships inside `amx-cli`; no Node toolchain or extra install needed.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://raw.githubusercontent.com/omeryasirkucuk/amx/main/docs/assets/studio-overview.png\" alt=\"AMX Studio Catalog landing page — sidebar with Catalog selected, four quick-action cards (Browse, New run, Ask, Audit), and a Recent activity feed\" width=\"900\"\u003e\n\u003c/p\u003e\n\nFull walkthrough at [`/studio`](https://amxcli.com/cli/studio/).\n\n## How it works\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://amxcli.com/assets/amx-flow.png\" alt=\"AMX flow — Profile, RAG, and Code agents feed evidence to an orchestrator that ranks suggestions; you review accept/edit/skip and AMX writes the approved text back as COMMENT ON COLUMN native DDL\" width=\"900\"\u003e\n\u003c/p\u003e\n\nEach agent runs independently, surfaces its own evidence, and assigns its own confidence. The orchestrator picks the narrower, defensible description and ranks up to N alternatives. You never apply anything you didn't approve.\n\n### A column, before and after\n\nA typical column in `orders`, the kind every analytics codebase has:\n\n```\norders.shipped_dt   DATE   NULL   -- (no comment)\n```\n\nWhat AMX produces, after you approve:\n\n```\nCOMMENT ON COLUMN orders.shipped_dt IS\n  'Date the carrier scanned the package at origin. Distinct from\n   order_dt (when the customer placed the order) and delivered_dt\n   (when the carrier recorded proof of delivery).';\n\nconfidence: high · logprob: 0.91\nsources: code (3 refs) · docs · db profile\n```\n\nEvery approval is recorded in local run history — re-evaluate later with `/history review` to see how the same column scores under a different model, prompt detail, or evidence mix.\n\n## Supported database backends\n\nPostgreSQL · Snowflake · Databricks (Unity Catalog) · BigQuery · MySQL / MariaDB · Oracle · SQL Server · Redshift · ClickHouse · DuckDB\n\nPer-backend setup, connection details, and the capability matrix live in the [Backends section](https://amxcli.com/backends/).\n\n## Supported LLM providers\n\nOpenAI · Anthropic · Google Gemini · DeepSeek · OpenRouter · Ollama · vLLM / LM Studio · any OpenAI-compatible endpoint\n\nProvider-specific guides (including OpenAI / Anthropic Batch mode and local-model setups) live in the [LLM providers section](https://amxcli.com/llm-providers/).\n\n## Next up\n\n- **dbt integration** — Connect dbt projects so the AMX code agent extracts table and column metadata from the transformation layer.\n- **MCP integration for docs and repo** — Expose the AMX repo and docs over the Model Context Protocol so LLM clients can query them as live context.\n- **CDC integration** — Detect schema changes in upstream sources and keep AMX metadata in sync.\n\nSee the [full roadmap](https://amxcli.com/roadmap/) for details.\n\n## Documentation\n\nFull user, operator, and contributor docs live at **[amxcli.com](https://amxcli.com/)** — concepts, the slash-command map, configuration, data sources, collaboration, troubleshooting, and the [Python API](https://amxcli.com/api/reference/) for headless use. Release notes are in [`CHANGELOG.md`](https://github.com/omeryasirkucuk/amx/blob/main/CHANGELOG.md) and on the [GitHub Releases page](https://github.com/omeryasirkucuk/amx/releases).\n\nRecent: Studio Lineage \u0026 Variations, Confidence Scoring, and explicit cache controls — see the [changelog](https://amxcli.com/changelog/).\n\nRecent: Studio Lineage \u0026 Variations, Confidence Scoring, and explicit cache controls — see the [changelog](https://omeryasirkucuk.github.io/amx-docs/changelog/).\n\n## Contributing \u0026 support\n\n- [Contributing guide](https://github.com/omeryasirkucuk/amx/blob/main/CONTRIBUTING.md) — development setup, branching, commit format, release process\n- [Security policy](https://github.com/omeryasirkucuk/amx/blob/main/SECURITY.md) — how to report a vulnerability\n- [Open an issue](https://github.com/omeryasirkucuk/amx/issues) — bugs, questions, feature requests\n\n## License\n\nApache-2.0 — see [`LICENSE`](https://github.com/omeryasirkucuk/amx/blob/main/LICENSE).\n\n---\n\n_This project is developed with the help of multiple AI coding agents._\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fomeryasirkucuk%2Famx","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fomeryasirkucuk%2Famx","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fomeryasirkucuk%2Famx/lists"}