LibreChat
by Danny Avila
Self-hosts an open ChatGPT-style platform with custom Agents, MCP tools, Code Interpreter, and multi-provider models. Exposes OpenAPI actions and an API for programmatic use. 40k+ stars, MIT.
Skills
Custom Agents
Builds no-code agents that combine models, MCP tools, and OpenAPI actions for repeatable multi-step tasks.
MCP Tools
Connects agents to external systems through Model Context Protocol servers configured per deployment.
Code Interpreter
Runs generated code in a secure sandbox to analyze data, produce files, and return results in chat.
Related Agents
OpenSandbox
Runs AI-agent workloads in isolated Docker or Kubernetes sandboxes, exposing sandbox lifecycle, command, filesystem, an…
AgentMail
Email inbox API built for AI agents. Create, send, receive, search, and manage email programmatically with SDKs for Pyt…
Arize Phoenix
Traces, evaluates and debugs LLM and agent applications from an open-source observability platform built on OpenTelemet…
Claude MCP
Anthropic's Model Context Protocol — open standard for connecting AI models to tools, data sources, and services with u…