{"data":{"slug":"berriai-litellm","name":"litellm","tagline":"The fastest, lightest AI Gateway","github_url":"https://github.com/BerriAI/litellm","owner":"BerriAI","repo":"litellm","owner_avatar_url":"https://avatars.githubusercontent.com/u/121462774?v=4","primary_language":"Python","stars":59051,"forks":11547,"topics":["ai-gateway","anthropic","azure-openai","bedrock","gateway","langchain","litellm","llm","llm-gateway","llmops","mcp-gateway","openai","openai-proxy","rust","rust-ai","vertex-ai"],"archived":false,"github_pushed_at":"2026-09-18T08:06:17+00:00","maintenance_label":"Very active","stars_delta_30d":3830,"url":"https://www.graphcanon.com/tools/berriai-litellm","markdown_url":"https://www.graphcanon.com/tools/berriai-litellm.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/berriai-litellm","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=berriai-litellm","description":"The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]","homepage_url":"https://docs.litellm.ai/docs/","license":"Other","open_issues":5212,"watchers":234,"ai_summary":"Rust core with Python SDK for calling over 100 LLM APIs in OpenAI or native format, featuring cost tracking, guardrails, load balancing, and logging","readme_excerpt":"### Verify Docker Image Signatures\n\nAll LiteLLM Docker images published to GHCR are signed with [cosign](https://docs.sigstore.dev/cosign/overview/). Every release is signed with the same key introduced in [commit `0112e53`](https://github.com/BerriAI/litellm/commit/0112e53046018d726492c814b3644b7d376029d0).\n\n**Verify using the pinned commit hash (recommended):**\n\nA commit hash is cryptographically immutable, so this is the strongest way to ensure you are using the original signing key:\n\n```bash\ncosign verify \\\n  --key https://raw.githubusercontent.com/BerriAI/litellm/0112e53046018d726492c814b3644b7d376029d0/cosign.pub \\\n  ghcr.io/berriai/litellm:<release-tag>\n```\n\n**Verify using a release tag (convenience):**\n\nTags are protected in this repository and resolve to the same key. This option is easier to read but relies on tag protection rules:\n\n```bash\ncosign verify \\\n  --key https://raw.githubusercontent.com/BerriAI/litellm/<release-tag>/cosign.pub \\\n  ghcr.io/berriai/litellm:<release-tag>\n```\n\nReplace `<release-tag>` with the version you are deploying (e.g. `v1.83.0-stable`).\n\n---\n\n---\n\n## Quick Start for Contributors\n\nThis requires uv to be installed.\n\n```bash\ngit clone https://github.com/BerriAI/litellm.git\ncd litellm\nmake install-dev    # Install development dependencies\nmake format         # Format your code\nmake lint           # Run all linting checks\nmake test-unit      # Run unit tests\nmake format-check   # Check formatting only\n```\n\nFor detailed contributing guidelines, see [CONTRIBUTING.md](CONTRIBUTING.md).\n\n> **📖 Contributing to documentation?** The LiteLLM docs have moved to a separate repository: [BerriAI/litellm-docs](https://github.com/BerriAI/litellm-docs). Please open doc PRs there. Docs are served at [docs.litellm.ai](https://docs.litellm.ai).","github_created_at":"2023-07-27T00:09:52+00:00","created_at":"2026-07-07T15:08:12.441998+00:00","updated_at":"2026-09-20T04:28:29.488919+00:00","categories":[{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"}],"tags":[{"slug":"ai-gateway","name":"ai-gateway"},{"slug":"anthropic","name":"anthropic"},{"slug":"azure-openai","name":"azure-openai"},{"slug":"bedrock","name":"bedrock"},{"slug":"langchain","name":"langchain"},{"slug":"litellm","name":"litellm"},{"slug":"llm","name":"llm"},{"slug":"llm-gateway","name":"llm-gateway"}],"trust":{"provenance":{"is_fork":false,"github_id":671269505,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:07:09.333Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":30,"days_since_push":0,"last_release_at":"2026-09-18T02:42:04Z","stars_delta_30d":3830,"open_issues_delta_30d":578},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":8,"high_count":0,"last_scan_at":"2026-09-18T08:07:11.090Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-09-18T08:07:07.985Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:07:07.985Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-09-18T08:07:07.985Z","managed_saas":false},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-09-18T08:07:07.985Z"},"languages":{"value":["python","javascript"],"source":"github.language+package.json+pyproject.toml","observed_at":"2026-09-18T08:07:07.985Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-09-18T08:07:07.985Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-09-18T08:07:07.985Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need a fast and lightweight AI gateway that supports over 100 LLM APIs in OpenAI or native format.","If you require robust cost tracking, guardrails, load balancing, and logging for your LLM API calls.","When you prefer a solution with a Rust core for performance and a Python SDK for ease of use.","If you are looking for a tool that supports multiple LLM providers including Bedrock, Azure, OpenAI, Anthropic, VertexAI, vLLM, and Nvidia NIM."],"when_not_to_use":["If you are working in an environment where Rust or Python is not supported or preferred.","When you need a tool that is not focused on performance and lightweight operations, as litellm is optimized for speed and efficiency.","If you require a tool that does not support a wide range of LLM APIs and providers, as litellm is designed to work with over 100 APIs.","When you need a tool that does not offer cost tracking, guardrails, load balancing, and logging, as these are key features of litellm."],"source":"enrich:decision_facts","observed_at":"2026-09-18T09:22:17.975Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"litellm is a Rust core with a Python SDK that serves as an AI gateway for over 100 LLM APIs, offering features like cost tracking, guardrails, load balancing, and logging."}]}}