AgentsKit vs. alternatives
How AgentsKit compares to LangChain.js, Vercel AI SDK, Mastra, and LlamaIndex.js across the surface area that actually matters in production.
AgentsKit is one of several ways to build agents in JavaScript. This page is opinionated but honest — each column lists what each framework genuinely optimizes for, with a link you can follow to verify.
If you only want the short version:
- Choose AgentsKit when you want one ecosystem across UI, runtime, tools, memory, retrieval, and production controls.
- Choose Vercel AI SDK when the main job is streaming chat in a React app.
- Choose LangChain.js when integration breadth matters more than tight contracts or bundle size.
- Choose Mastra when you want an agent-first TS framework and like its workflow model.
- Choose LlamaIndex.js when retrieval is the center of the product.
#Positioning in one line
| Framework | Positioning |
|---|---|
| AgentsKit | One toolkit — same contracts across chat UI, runtime, memory, RAG, tools, observability. Zero lock-in; swap pieces without breaking the agent. |
| LangChain.js | Huge integration catalog. Heavy on abstractions; focused on chains + agents. |
| Vercel AI SDK | Best-in-class streaming + React hooks. Chat-first; less coverage beyond the message loop. |
| Mastra | TypeScript-first agent framework with workflows + memory built-in. |
| LlamaIndex.js | RAG-first. Strong indexing + query engines. |
#Where AgentsKit tends to win
- You want one mental model across browser, terminal, server, and jobs.
- You want to start with a small slice and grow into a fuller stack without replacing the foundation.
- You care about runtime contracts, bundle size, and long-term substitutability.
- You want a stack that can cover support agents, research agents, code agents, and internal copilots with the same substrate.
See: Architecture at a glance · Use cases
#Feature comparison
| Capability | AgentsKit | LangChain.js | Vercel AI SDK | Mastra | LlamaIndex.js |
|---|---|---|---|---|---|
| Streaming chat controller | ✅ | ✅ | ✅ | ✅ | ✅ |
React hook (useChat) | ✅ | partial | ✅ | partial | — |
| Vue / Svelte / Solid / Angular / RN bindings | ✅ (same contract) | — | community | — | — |
| Terminal UI | ✅ (@agentskit/ink) | — | — | — | — |
| ReAct runtime | ✅ | ✅ | — | ✅ | ✅ |
| Deterministic replay | ✅ (@agentskit/eval/replay) | — | — | — | — |
| Multi-agent topologies (supervisor / swarm / blackboard / hierarchical) | ✅ | partial (LangGraph) | — | partial | — |
| Durable execution (step log) | ✅ | via LangGraph | — | ✅ | — |
| Human-in-the-loop primitives | ✅ (@agentskit/core/hitl) | partial | — | ✅ | — |
| Built-in prompt injection detector | ✅ (@agentskit/core/security) | — | — | — | — |
| Built-in signed audit log | ✅ (@agentskit/observability) | — | — | — | — |
| Token-bucket rate limiting | ✅ | — | — | — | — |
| Mandatory tool sandbox policy | ✅ (@agentskit/sandbox) | — | — | — | — |
| Bidirectional MCP bridge | ✅ (@agentskit/tools/mcp) | client only | partial | client only | client only |
| Vector backends | pgvector, Pinecone, Qdrant, Chroma, Upstash, Redis, file | 30+ | — | Postgres, SQLite | 30+ |
| Document loaders (URL / GitHub / Notion / Confluence / Drive / PDF) | ✅ | ✅ (largest catalog) | — | partial | ✅ |
| Evals in CI (JUnit + step-summary annotations) | ✅ (@agentskit/eval/ci) | partial | — | — | partial |
| Core bundle size | < 10 KB gzipped | > 100 KB | ~30 KB | ~50 KB | > 100 KB |
| Zero runtime deps (core) | ✅ | — | — | — | — |
| Edge / Deno / Bun runtime | ✅ | partial | ✅ | partial | partial |
"partial" means the capability exists but requires stitching multiple packages or a community port — not a built-in, contract-level feature.
#When to pick which
- AgentsKit — you want one mental model across web, terminal, mobile, and server; you care about bundle size, observability, and production gates (HITL, rate limits, audit, sandbox).
- LangChain.js — you need the widest catalog of prebuilt integrations today and are happy to wrap them yourself.
- Vercel AI SDK — you only need a streaming chat hook inside a Next.js / React app and don't want extra surface area.
- Mastra — you want a workflow-first agent framework with built-in memory and agent registry.
- LlamaIndex.js — your product is a retrieval engine; you want sophisticated query engines out of the box.
#Migration guides
#Migration shortcuts
- Coming from Vercel AI SDK and you want more than chat: start with Build your first agent and then migrate from Vercel AI SDK.
- Coming from LangChain.js and you want a smaller, tighter stack: start with Architecture at a glance and then migrate from LangChain.js.
- Coming from Mastra and you want slimmer contracts: start with Use cases and then migrate from Mastra.
#See also
Explore nearby
- PeerGet started
Build your first agent, learn the stack, then go deeper.
- PeerWhich package do I need?
A 5-question decision tree from your use case to the one or two AgentsKit packages you actually need to install.
- PeerArchitecture at a glance
See the AgentsKit ecosystem by layer, how the contracts compose, and how teams usually adopt it over time.