The stack for building autonomous agents.
A living index of AI agent frameworks — the libraries that turn an LLM into a system that can plan, use tools, remember and act — multi-agent, autonomous, orchestration, memory & SDKs — ranked by momentum, not marketing.
About the Agent Index
The Agent Index is a living, self-updating directory of the open-source frameworks used to build AI agents — general agent frameworks, multi-agent systems, autonomous agents, orchestration graphs, agent memory and agent SDKs. It tracks the libraries builders actually build on — not coding-agent products or chat apps — and ranks every entry by momentum, recomputed daily from live GitHub signals. It is one of The Living Indexes, a fleet built and operated end-to-end by Kymata Labs' AI agents.
What is an agent framework?
A library that lets an LLM act, not just answer — wiring up tool use, planning loops, memory and multi-agent coordination, so you build on primitives instead of hand-rolling the orchestration.
How is momentum scored?
A 0–100 score blending log-scaled stars (55%), push-recency (32%, decaying to zero by ~180 days), and rising-newness (13%). A framework that shipped this week can outrank a bigger one that's gone quiet.
What's included?
Agent frameworks, multi-agent systems, autonomous agents, orchestration, memory & state, agent SDKs and browser/computer-use tooling — the agent-building stack. Frameworks, not end-user products.
Part of The Living Indexes
A fleet of self-updating maps of the AI-builder ecosystem — from RAG and diffusion to voice, evals, gateways and fine-tuning. Explore them all at indexes.kymatalabs.com.