Langbase is a serverless AI developer platform for building, deploying, and scaling AI agents and applications. Its composable primitives - Pipes (agents), Memory (managed RAG), Threads, Agent (one API over 100+ LLMs), Tools, Parser, Chunker, and Embed - are exposed through a single Bearer-authenticated REST API at api.langbase.com, with Server-Sent Events (SSE) streaming for generative endpoints.
APIs.json: https://raw.githubusercontent.com/api-evangelist/langbase/refs/heads/main/apis.yml
- AI
- Agents
- RAG
- LLM
- Serverless
- Created: 2026-07-01
- Modified: 2026-07-01
Run, create, update, and list Pipes - composable, deployable AI agents with a system prompt, model, tools, variables, and memory. POST /v1/pipes/run executes a Pipe over a message array and streams token deltas as Server-Sent Events when stream is true.
- Human URL: https://langbase.com/docs/api-reference/pipe
- Base URL:
https://api.langbase.com/v1
- Pipes
- Agents
- Completions
- Documentation
- API Reference
- OpenAPI — OpenAPI Specification
- Postman Collection — Postman Collection 2.1
- Open Collection — Open Collection 1.0
A single liquid AI mesh endpoint (POST /v1/agent/run) that runs a prompt against 100+ LLMs from all top providers using a provider:model_id string, with tools, generation controls, and SSE streaming. Bring-your-own LLM keys are supported via the LB-LLM-Key header.
- Human URL: https://langbase.com/docs/api-reference/agent
- Base URL:
https://api.langbase.com/v1
- Agent
- LLM
- Multi-Provider
- Documentation
- API Reference
- OpenAPI — OpenAPI Specification
- Postman Collection — Postman Collection 2.1
- Open Collection — Open Collection 1.0
Managed, serverless RAG. Create and list memory stores, upload and manage documents, and retrieve semantically similar chunks (POST /v1/memory/retrieve) with a topK control and metadata filters, without running your own vector database or embedding pipeline.
- Human URL: https://langbase.com/docs/api-reference/memory
- Base URL:
https://api.langbase.com/v1
- Memory
- RAG
- Vector Store
- Documentation
- API Reference
- OpenAPI — OpenAPI Specification
- Postman Collection — Postman Collection 2.1
- Open Collection — Open Collection 1.0
Persist and manage conversation state. Create, get, update, and delete threads, and append or list messages, so multi-turn agent conversations keep their history server-side and can be resumed via a thread identifier.
- Human URL: https://langbase.com/docs/api-reference/threads
- Base URL:
https://api.langbase.com/v1
- Threads
- Conversation
- State
- Documentation
- API Reference
- OpenAPI — OpenAPI Specification
- Postman Collection — Postman Collection 2.1
- Open Collection — Open Collection 1.0
Managed agent tools. POST /v1/tools/web-search runs a live web search (via providers such as Exa) returning URLs and extracted content, and POST /v1/tools/crawl fetches and extracts content from one or more web pages for agents to ground on.
- Human URL: https://langbase.com/docs/api-reference/tools
- Base URL:
https://api.langbase.com/v1
- Tools
- Web Search
- Crawl
- Documentation
- API Reference
- OpenAPI — OpenAPI Specification
- Postman Collection — Postman Collection 2.1
- Open Collection — Open Collection 1.0
Extract clean text from uploaded documents (PDF, CSV, XLSX, XLS, and more, up to 10 MB) via a multipart POST /v1/parser, as the ingestion front door for RAG and content pipelines.
- Human URL: https://langbase.com/docs/api-reference/parser
- Base URL:
https://api.langbase.com/v1
- Parser
- Documents
- Extraction
- Documentation
- API Reference
- OpenAPI — OpenAPI Specification
- Postman Collection — Postman Collection 2.1
- Open Collection — Open Collection 1.0
Split large text into overlapping, retrieval-ready chunks (POST /v1/chunker) with configurable chunkMaxLength and chunkOverlap, for building RAG and search indexes.
- Human URL: https://langbase.com/docs/api-reference/chunker
- Base URL:
https://api.langbase.com/v1
- Chunker
- RAG
- Preprocessing
- Documentation
- API Reference
- OpenAPI — OpenAPI Specification
- Postman Collection — Postman Collection 2.1
- Open Collection — Open Collection 1.0
Generate embedding vectors for up to 100 text chunks per request (POST /v1/embed) using OpenAI, Cohere, or Google embedding models, defaulting to openai:text-embedding-3-large.
- Human URL: https://langbase.com/docs/api-reference/embed
- Base URL:
https://api.langbase.com/v1
- Embeddings
- Vectors
- RAG
- Documentation
- API Reference
- OpenAPI — OpenAPI Specification
- Postman Collection — Postman Collection 2.1
- Open Collection — Open Collection 1.0
Durable, step-based orchestration for composing agents, memory, and tools into multi-step AI workflows with retries and timeouts. Workflows compose the underlying Agent, Pipes, Memory, and Tools API calls into a single reliable execution.
- Human URL: https://langbase.com/docs/workflows
- Base URL:
https://api.langbase.com/v1
- Workflows
- Orchestration
- Agents
- Documentation
- OpenAPI — OpenAPI Specification
- Postman Collection — Postman Collection 2.1
- Open Collection — Open Collection 1.0
FN: Kin Lane Email: kin@apievangelist.com