agents
agent-frameworkStable
An Open-source Framework for Data-centric, Self-evolving Autonomous Language Agents
Stars
5,932
Δ stars 7d
+7
Δ stars 30d
—
Forks
480
Contributors
26
npm DL / wk
—
PyPI DL / wk
—
Language
Python
Last push
2024-09-26
About agents
[🤖Project] [📄Paper] [📝Docs] [🌟Overview] [🔧Installation] [🚩Citation] Agent symbolic learning is a systematic framework for training language agents, which is inspired by the connectionist learning procedure used for training neural nets. We make an analogy between language agents and neural nets: the agent pipeline of an agent corresponds to the computational graph of a neural net, a node in the agent pipeline corresponds to a layer in the neural net, and the prompts and tools for a node correspond to the weights of a layer. In this way, we are…
Read the full README on GitHub →
agents growth signals this week
- Gained 7 stars in the last 7 days
Growth score: 2/100 week of 2026-06-08
Signal history
| Week | Score | Δ★ | Signal |
|---|---|---|---|
| 2026-06-08 | 2 | +7 | Stable |
agents alternatives
Projects in the same category, closest in size — picked by data, not opinion.
See all agent-framework projects ranked by growth →
Frequently asked questions
- Is agents still maintained?
- Activity is low: the last push was on 2024-09-26 (627 days before our latest snapshot).
- Is agents growing?
- It is stable this week, with a growth score of 2/100. See the weekly history above.
- What are the best agents alternatives?
- Closest by category and size in our data: TaskWeaver, AgentOps, AG2 — full list with live signals above.
Embed this badge
Show your project's live signal in your README — it updates weekly with the data.
Tracked since 2026-06-10 · data as of 2026-06-15 · 44 open issues ·