GPTSwarm
ai-agentNo score yet
๐ The First Self-Improving agents with RL / Prompting Optimization
Stars
1,010
ฮ stars 7d
โ
ฮ stars 30d
โ
Forks
99
Contributors
7
npm DL / wk
โ
PyPI DL / wk
โ
Language
Python
Last push
2026-02-05
About GPTSwarm
๐ **GPTSwarm is a graph-based framework for LLM-based agents, providing two high-level features:** At a granular level, GPTSwarm is a library that includes the following components: Here is the edge optimization process that updates edge probabilities toward improvement of the benchmark score. Notice that within an agent, the edges are fixed, whereas the inter-agent connections are getting optimized towards either edge pruning (value 0, blue) or creation (value 1, red).
Read the full README on GitHub โ
GPTSwarm alternatives
Projects in the same category, closest in size โ picked by data, not opinion.
See all ai-agent projects ranked by growth โ
Frequently asked questions
- Is GPTSwarm still maintained?
- Activity is low: the last push was on 2026-02-05 (125 days before our latest snapshot).
- What are the best GPTSwarm alternatives?
- Closest by category and size in our data: ix, llm_agents, evo.ninja โ full list with live signals above.
Embed this badge
Show your project's live signal in your README โ it updates weekly with the data.
Tracked since 2026-06-10 ยท data as of 2026-06-10 ยท 2 open issues ยท