\n\n # Palico AI - Tech-Stack for Iterative Development\n
\n
\n Documentation |\n Quickstart |\n Agents |\n Memory |\n Tracing |\n Evaluations |\n SDKs |\n Deployment\n
\n \n\n
\n \n \n \n \n \n \n\n\n \n
\n\n- ✅ Improve performance with Experiments and Evals ([docs](https://docs.palico.ai/guides/experiments))
\n- ✅ Debug issues with logs and traces ([docs](https://docs.palico.ai/guides/telemetry))
\n- ✅ Integrate with your frontend with ClientSDKs or REST API ([docs](https://docs.palico.ai/client-sdk/introduction))
\n- ✅ Setup Continous Integration and Pull-Request Previews ([docs](https://docs.palico.ai/guides/deployment))
\n- ✅ Manage your application from a control panel ([docs](https://docs.palico.ai/components#palico-studio))
\n\n> [!TIP]\n> ⭐️ **Star this repo** to get release notifications for new features.\n>\n> \n\n## ⚡ Get started in seconds ⚡\n\n```bash\nnpx palico init
\n```\n\nCheckout our [quickstart](https://docs.palico.ai/) guide.\n\n### Overview of your Palico App\n\nhttps://github.com/user-attachments/assets/8c8a1c62-f70d-45a5-82f7-21b2073ba9f0\n\n## 🛠️ Building your Application\n\n### Build your application with complete flexibility\n\nWith Palico, you have complete control over the implementation details of your LLM application. Build any application by creating a `Chat` function.\n\n```typescript src/agents/my_agent/index.ts {5,17}\nimport { Chat } from '@palico-ai/app';\nimport OpenAI from 'openai';\n\n// 1. implement the Chat type\nconst handler: Chat = async ({ userMessage }) => {\n // 2. implement your application logic\n const response = await openai.chat.completions.create({\n model: 'gpt-3.5-turbo-0125',\n messages: [{ role: 'user', content: userMessage }],\n });\n return {\n message: response.choices[0].message.content,\n };\n};\n\n// 3. export the handler\nexport default handler;\n```\n\nLearn more about building your application with palico ([docs](https://docs.palico.ai/guides/build)).\n\n### Build complex interactions with powerful primitives\n\n| Feature | Description |\n| --------------------------------------------------------------------- | ------------------------------------------------------------------------------------- |\n| [Streaming](https://docs.palico.ai/guides/streaming) | Stream messages, data, and intermediate steps to your client-app |\n| [Memory Management](https://docs.palico.ai/guides/conversation_state) | Store conversation states between request without managing any storage infrastructure |\n| [Tool Executions](https://docs.palico.ai/guides/agents) | Build Agents that can execute tools on client-side and server-side |\n| [Feature Flags](https://docs.palico.ai/guides/feature_flag) | Easily swap models, prompts,","github_created_at":"2024-03-12T04:09:45+00:00","created_at":"2026-07-11T12:00:17.149892+00:00","updated_at":"2026-09-20T06:58:49.393185+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"},{"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"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"ai","name":"ai"},{"slug":"anthropic","name":"anthropic"},{"slug":"autogen","name":"autogen"},{"slug":"docker","name":"docker"},{"slug":"full-stack","name":"full-stack"},{"slug":"javascript","name":"javascript"},{"slug":"langchain","name":"langchain"},{"slug":"langchain-js","name":"langchain-js"}],"trust":{"provenance":{"is_fork":false,"github_id":770735319,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T06:58:47.332Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":662,"last_release_at":"2024-11-14T02:52:26Z","stars_delta_30d":0,"open_issues_delta_30d":-1},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T12:00:18.607Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-09-20T06:58:48.355Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-09-20T06:58:48.355Z"},"languages":{"value":["typescript","javascript"],"source":"github.language+package.json","observed_at":"2026-09-20T06:58:48.355Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-20T06:58:48.355Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["Requires Docker for certain functionalities","Primarily uses TypeScript, proficiency with this language is beneficial"],"min_ram_gb":null,"requires_docker":true},"constraints":{"min_ram_gb":null,"requires_docker":true},"when_to_use":["When your project requires comprehensive tools for building, optimizing, and deploying AI apps specifically in a TypeScript environment","If you need an entire suite spanning from framework development through to observability features tailored towards TypeScript-based projects"],"when_not_to_use":["If your primary programming language is not TypeScript or Node.js, as palico-ai heavily relies on these technologies","When seeking a solution that requires less integration effort with existing frameworks outside of the listed supported areas such as anthropic, autogen, and portkey"],"source":"enrich:decision_facts","observed_at":"2026-07-17T00:07:02.181Z"},"constraint_facets":{"min_ram_gb":null,"requires_docker":true},"decision_summary":[{"label":"Requirements","value":"Requires Docker; Requires Docker for certain functionalities; Primarily uses TypeScript, proficiency with this language is beneficial"},{"label":"Adopt for","value":"palico-ai builds, improves performance of, and deploys AI applications using TypeScript. It encompasses technologies from framework development to evaluation."},{"label":"License detail","value":"MIT License allows wide reuse within any project but requires copyright and license notice preservation in source distributions."}]}}