{"data":{"slug":"mnfst-manifest","name":"manifest","tagline":"Connect Your Agents And Harnesses With Any Provider","github_url":"https://github.com/mnfst/manifest","owner":"mnfst","repo":"manifest","owner_avatar_url":"https://avatars.githubusercontent.com/u/8403534?v=4","primary_language":"TypeScript","stars":7589,"forks":519,"topics":["ai","ai-","ai-sdk","anthropic","byok","cost-tracking","gateway","hermes-agent","llm-observability","llm-router","open-source","openai-api","openclaw","subscription","token-tracking"],"archived":false,"github_pushed_at":"2026-10-18T19:40:19+00:00","maintenance_label":"Very active","stars_delta_30d":75,"url":"https://www.graphcanon.com/tools/mnfst-manifest","markdown_url":"https://www.graphcanon.com/tools/mnfst-manifest.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/mnfst-manifest","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=mnfst-manifest","description":"Open Source LLM Gateway 🦚","homepage_url":"https://manifest.build","license":"MIT","open_issues":52,"watchers":29,"ai_summary":"A framework that enables the integration and connection of AI agents across different providers.","readme_excerpt":"<p align=\"center\">\n  <picture>\n    <source media=\"(prefers-color-scheme: dark)\" srcset=\".github/assets/logo-white.svg\" />\n    <source media=\"(prefers-color-scheme: light)\" srcset=\".github/assets/logo-dark.svg\" />\n    <img src=\".github/assets/logo-dark.svg\" alt=\"Manifest LLM Gateway\" height=\"53\" title=\"Manifest LLM Gateway\"/>\n  </picture>\n</p>\n<p align=\"center\">\nAI Agents that don't break\n</p>\n\n\n\n---\n\n<p align=\"center\">\n  <a href=\"https://render.com/deploy?repo=https://github.com/mnfst/llm-gateway\" target=\"_blank\" rel=\"nofollow\"><img src=\"https://img.shields.io/badge/Deploy%20on-Render-46E3B7?style=for-the-badge&amp;logo=render&amp;logoColor=white\" alt=\"Deploy on Render\" /></a>\n  <a href=\"https://railway.com/deploy/wild-wild\" target=\"_blank\" rel=\"nofollow\"><img src=\"https://img.shields.io/badge/Deploy%20on-Railway-0B0D0E?style=for-the-badge&amp;logo=railway&amp;logoColor=white\" alt=\"Deploy on Railway\" /></a>\n  <a href=\"https://console.aws.amazon.com/cloudformation/home?region=us-east-1#/stacks/quickcreate?stackName=manifest&amp;templateURL=https%3A%2F%2Fmnfst-manifest-deploy-templates.s3.us-east-1.amazonaws.com%2Fmanifest.yaml\" target=\"_blank\" rel=\"nofollow\"><img src=\"https://img.shields.io/badge/Deploy%20on-AWS-232F3E?style=for-the-badge&amp;logo=amazonwebservices&amp;logoColor=white\" alt=\"Deploy on AWS\" /></a>\n  <a href=\"https://ssh.cloud.google.com/cloudshell/editor?cloudshell_git_repo=https%3A%2F%2Fgithub.com%2Fmnfst%2Fllm-gateway&amp;cloudshell_workspace=deploy%2Fgcp&amp;cloudshell_tutorial=TUTORIAL.md&amp;cloudshell_image=gcr.io/ds-artifacts-cloudshell/deploystack_custom_image&amp;shellonly=true\" target=\"_blank\" rel=\"nofollow\"><img src=\"https://img.shields.io/badge/Deploy%20on-GCP-4285F4?style=for-the-badge&amp;logo=googlecloud&amp;logoColor=white\" alt=\"Deploy on GCP\" /></a>\n</p>\n\n<p align=\"center\">\n  <a href=\"https://github.com/mnfst/llm-gateway/stargazers\"><img src=\"https://img.shields.io/github/stars/mnfst/llm-gateway?style=flat\" alt=\"GitHub stars\" /></a>\n  &nbsp;\n  <a href=\"https://hub.docker.com/r/manifestdotbuild/manifest\"><img src=\"https://img.shields.io/docker/pulls/manifestdotbuild/manifest?color=2496ED&label=docker%20pulls\" alt=\"Docker pulls\" /></a>\n  &nbsp;\n  <a href=\"https://hub.docker.com/r/manifestdotbuild/manifest/tags\"><img src=\"https://img.shields.io/docker/image-size/manifestdotbuild/manifest/latest?color=2496ED&label=image%20size\" alt=\"Docker image size\" /></a>\n  &nbsp;\n  <a href=\"https://github.com/mnfst/llm-gateway/actions/workflows/ci.yml\"><img src=\"https://img.shields.io/github/actions/workflow/status/mnfst/llm-gateway/ci.yml?branch=main&label=CI\" alt=\"CI status\" /></a>\n  &nbsp;\n  <a href=\"https://app.codecov.io/gh/mnfst/llm-gateway\"><img src=\"https://img.shields.io/codecov/c/github/mnfst/llm-gateway?label=coverage\" alt=\"Codecov\" /></a>\n  &nbsp;\n  <a href=\"LICENSE\"><img src=\"https://img.shields.io/github/license/mnfst/llm-gateway?color=blue\" alt=\"license\" /></a>\n  &nbsp;\n  <a href=\"https://discord.gg/FepAked3W7\"><img src=\"https://img.shields.io/badge/Discord-Join-5865F2?logo=discord&logoColor=white\" alt=\"Discord\" /></a>\n</p>\n\n<p align=\"center\">\n<a href=\"https://trendshift.io/repositories/12890\" target=\"_blank\"><img src=\"https://trendshift.io/api/badge/repositories/12890\" alt=\"mnfst%2Fllm-gateway | Trendshift\" style=\"width: 250px; height: 55px;\" width=\"250\" height=\"55\"/></a>\n</p>\n\n## What is Manifest LLM Gateway?\n\nManifest LLM Gateway is an open-source LLM gateway for AI agents and apps. Connect your API keys, subscriptions, and local models to one OpenAI-compatible endpoint, and each query goes to the right model. No single-provider lock-in.\n\n- 🔀 Custom Routing: API keys, Subscriptions, Local models, Custom providers\n- 💾 Full Body Logs for Success and Error Messages\n- 📊 Track every single dollar, setup notifications and limits\n- 🚑 Fallback on different models when queries fail, Self-heals your bad requests\n\n## Quick start\n\n### Cloud version\n\nGo to [app.manifest.build](https://app.manifest.build)","github_created_at":"2022-09-27T16:33:35+00:00","created_at":"2026-07-15T10:40:54.244709+00:00","updated_at":"2026-10-19T06:00:33.186409+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"}],"tags":[{"slug":"ai-agents","name":"ai-agents"},{"slug":"llm-observability","name":"llm-observability"}],"trust":{"provenance":{"is_fork":false,"github_id":542185751,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-10-19T06:00:32.082Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":30,"days_since_push":0,"last_release_at":"2026-10-16T18:34:54Z","stars_delta_30d":75,"open_issues_delta_30d":-58},"security_summary":{"last_scan_at":"2026-07-15T10:40:56.598972+00:00","scan_profile":"deps","status":"no_lockfile","critical_count":0,"high_count":0,"medium_count":0,"low_count":0,"scanner":"osv@v1","scan_id":"ad79339f-176b-467e-94ce-33e19e0c7d7b","pending_review_count":0}},"capability_facts":{"mcp":{"method":"github-tree-and-contents@2","reason":"Repository inspection failed; server presence is unknown.","source":"repo_scan","status":"unknown","observed_at":"2026-10-19T06:00:32.525Z","server_manifest":null},"scan":{"method":"github-tree-and-contents@2","source":"repo_scan","status":"error","version":2,"coverage":{"scope":"bounded-repository-manifests","tree_complete":false,"selected_files":0,"candidate_files":0},"source_url":"https://github.com/mnfst/manifest","observed_at":"2026-10-19T06:00:32.525Z","observations":[{"path":"@revision","reason":"http-301","status":"error","revision":null,"source_url":"https://github.com/mnfst/manifest","http_status":301,"observed_at":"2026-10-19T06:00:32.692Z"}]},"languages":{"value":["typescript"],"source":"github.language","observed_at":"2026-10-19T06:00:32.525Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-10-19T06:00:32.525Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need to establish connections between multiple AI providers without altering the core functionality or architecture of your existing systems.","For projects requiring detailed observability features like token and cost-tracking for efficient monitoring of resources used by different AI agents."],"when_not_to_use":["If your project strictly requires use cases with non-TypeScript languages, as this would necessitate additional integration work.","When you require a mature framework; given Manifest's beta status, it might not be the best choice for production environments sensitive to potential bugs or incomplete features."],"source":"enrich:decision_facts","observed_at":"2026-07-17T07:20:50.889Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Unverified catalog guidance: Manifest is a TypeScript framework under MIT license that enables integration of AI agents across various providers, with an emphasis on observability and tracking mechanisms such as token and cost-tracking."}]}}