agentskit.js

AgentsKit.js

The JavaScript ecosystem for building AI agents — UI, runtime, tools, memory, RAG, observability, and production guardrails.

Agents shouldn't be a monolith. AgentsKit.js is a family of small, plug-and-play packages covering the whole agent lifecycle in JavaScript: chat UIs, autonomous runtimes, tools, skills, memory, RAG, observability, evaluation, sandboxing. Install what you need. Everything else stays out of your bundle.

#Start here

Pick a path by what you're shipping.

#Build path

If you are evaluating AgentsKit, this is the shortest path to understanding the product:

  1. Build your first agent — see provider + runtime + tools + memory + observability working together.
  2. Architecture at a glance — understand which layer owns what.
  3. Production — add observability, security, evals, and CLI workflows.
  • Support agent — customer support with memory, tools, and escalation.
  • Research agent — web research, structured summaries, and background jobs.
  • Code agent — repository-aware automation with safe tool use.
  • Internal copilot — company knowledge with RAG and production controls.

#The substrate

Six stable contracts. Every package is an implementation of one.

ContractRoleDeep dive
AdapterLLM provider seamconcept · implementations
ToolFunction the model callsconcept · implementations
SkillDeclarative personaconcept · implementations
MemoryChat history + vector stateconcept · implementations
RetrieverContext fetchingconcept · implementations
RuntimeThe loop that composes them allconcept · implementations

Learn the six once; swap implementations forever. The mental model walks through how they compose.

#What's inside

  • 19 packages under @agentskit/* — foundation, providers, UI bindings, runtime, capabilities, observability, infrastructure. Full index.
  • 7 framework bindings sharing one useChat contract. UI matrix.
  • 20+ provider adapters (hosted + local + embedders). Providers.
  • 60+ recipes grouped by theme. Recipes.
  • Open specs — A2A, Manifest, Eval Format, AgentSchema — portable JSON. Specs.

#Keep reading

  • Comparison — AgentsKit vs LangChain, Vercel AI, Mastra, LlamaIndex.
  • Migrating — port from Vercel AI SDK, LangChain.js, Mastra.
  • For agents — dense LLM-friendly reference per contract.
  • Examples — live interactive demos.
  • Contribute — built in the open. Your PR helps.
  • Discord — Office Hours every Friday; direct line to maintainers.
✎ Edit this page on GitHub·Found a problem? Open an issue →·How to contribute →

On this page