Vibe Coding Discover

AI Agents

🤖 A full-stack Agent Chat Runtime for pre-production validation, built with act, TypeScript, and LangGraph JS combining streaming, multimodal, HITL, and tools with durable Task/Step execution, retry budgets, idempotency, compensation, distributed locks, context governance, OpenTelemetry tracing, model fallback, cost tracking, and Opik evaluation.

★ 13317 forksTypeScriptCustomHsienW

Full-stack LangGraph.js agent chat runtime with streaming, multimodal input, human-in-the-loop workflows, native and MCP tools, and durable task execution features. Includes a React UI, API gateway, OpenTelemetry tracing, and optional Opik evaluation.

Use Cases

Build and validate multi-agent chat workflowsConduct tool-assisted deep research with source verificationRun math-solving agentsAdd human approval or clarification steps to agent workflowsAnalyze image inputs with vision modelsConnect agents to native tools and MCP serversTrace and evaluate agent behavior

Built With

Language
TypeScript
Frameworks
LangGraph.js · React · OpenTelemetry · Opik · MCP

Tags

multi-agent · agent-runtime · chatbot · streaming · multimodal · human-in-the-loop · tool-calling · MCP · durable-execution · model-fallback · observability · evaluation