Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Make your agents improve themselves. Reflexio is an AI agent self-improvement harness that enables your AI agents to continuously learn from real user interactions.
| Date | Stars |
|---|---|
| 2026-07-31 | 327 |
| 2026-08-06 | 327 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<p align="center">
<a href="https://github.com/reflexio-ai/reflexio">
<img src="docs/images/banner.png" width="800px" alt="Reflexio - Make Your Agents Improve Themselves">
</a>
</p>
<div align="center">
[](https://www.python.org/)
[](LICENSE)
[](https://pypi.org/project/reflexio-ai/)
[](https://pepy.tech/project/reflexio-ai)
[](reflexio/benchmarks/retrieval_latency/results/report.md)
[](https://github.com/ReflexioAI/reflexio/stargazers)
[](https://discord.gg/7fnCxahase)
[Quick Start](#quick-start) · [Features](#features) · [Integrations](#integrations) · [SDK](#sdk-usage) · [CLI](reflexio/cli/README.md) · [Architecture](#architecture) · [Docs](https://www.reflexio.ai/docs) · [Community](#community) · [Contributing](#contributing)
</div>
---
<p align="center">
<b>81% fewer planning steps</b> · <b>72% less tokens</b> · on real GDPVal knowledge-work tasks, <br/>
<i>on top of</i> what a SOTA self-improving Hermes agent already learns on its own.<br/>
<a href="benchmark/gdpval/RESULTS.md"><b>See the benchmark →</b></a>
</p>
---
### Migration from claude_code integration (removed in this release)
The `reflexio setup claude-code` command and its hook files have been removed.
The replacement is **[claude-smart](https://github.com/ReflexioAI/claude-smart)**,
a standalone Claude Code plugin distributed via npm.
*This migration only removes the **hook/plugin installation** path. The local
`claude-code` LLM provider routing (used to call Anthropic via the Claude Code
CLI binary as a model backend) remains available — only remove obsolete hook
entries, not your provider configuration.*
**If you had the old integration installed**, your `.claude/settings.json` (per-project)
or `~/.claude/settings.json` (global) likely has hook entries referencing files that no longer exist.
Open the file and remove any `hooks` entries that reference paths under `reflexio/integrations/claude_code/`
or `integrations/claude_code/`. Then run `npx claude-smart install` (or use the Claude Code plugin marketplace)
for the modern equivalent.
---
## What is Reflexio?
Reflexio is an **AI agent self-improvement harness** that enables your AI agents to continuously learn from real user interactions. It turns user corrections into persisted behavioral improvements for agents and capturing successful execution paths for reuse.
What one user teaches, every user benefits from.
As your agent is used more, it becomes smarter, faster, and more effective at solving domain-specific tasks.
The moat for AI agents is what your agent learns from every interaction it handles.
Our vision is that AI systems should get better with every interaction.
> **Benchmarked on GDPVal**: on 4 of 5 real knowledge-work tasks from OpenAI's public GDPVal benchmark, Reflexio cuts a **median −81% planning steps and −72% tokens** on a Hermes agent running `minimax/MiniMax-M2.7` — measured against a *warm baseline*: the same agent re-running the task after it has already learned from itself. In other words, Reflexio's savings come **on top of** what a SOTA self-improving agent has learnt on its own. See the full writeup → [benchmark/gdpval/RESULTS.md](benchmark/gdpval/RESULTS.md).
```mermaid
flowchart LR
A[AI Agent] -->|conversations| B[Reflexio]
G[Human Expert] -->|ideal responses| B
B --> C[User Profiles]
B --> D[Playbook Extraction]
D --> E[Playbook Aggregation]
B --> F[Success Evaluation]
```
Publish conversationExcerpt of 14,516 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:3ed319b792033db8, llm:Repository description and topics: 'Make your agents improve themselves. Reflexio is an AI agent self-improvement harness that enables your AI agents to continuously learn from real user interactions.' Topics: self-improvement, self-improving-agent, self-improving-ai, self-learning.
matched fp:3ed319b792033db8, llm:Repository description and topics: 'Make your agents improve themselves. Reflexio is an AI agent self-improvement harness that enables your AI agents to continuously learn from real user interactions.' Topics: self-improvement, self-improving-agent, self-improving-ai, self-learning.
matched fp:3ed319b792033db8, llm:Repository description and topics: 'Make your agents improve themselves. Reflexio is an AI agent self-improvement harness that enables your AI agents to continuously learn from real user interactions.' Topics: self-improvement, self-improving-agent, self-improving-ai, self-learning.