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.
This repository also configures its own agents. See what reflexio tells them →
Skill Claude CodeCodex
Captures user facts and procedural corrections into .reflexio/ so the agent learns across sessions. Use when: (1) user states a preference, fact, config, or constraint; (2) user corrects the agent and confirms the fix with an explicit 'good'/'perfect' or by moving on without re-correcting for 1-2 turns; (3) at start…
Skill Claude CodeCodex
Run a full-sweep consolidation over all .reflexio/ files — TTL sweep + n-way cluster merge. Use when the user asks to 'clean up reflexio', 'consolidate memory', 'deduplicate playbooks', or suspects drift across sessions.
Skill Claude CodeCodex
Captures user facts and procedural corrections into .reflexio/ so the agent learns across sessions. Use when: (1) user states a preference, fact, config, or constraint; (2) user corrects the agent and confirms the fix with an explicit 'good'/'perfect' or by moving on without re-correcting for 1-2 turns; (3) at start…
Skill Claude CodeCodex
When to use: The user explicitly asks to delete all locally-stored skills/preferences. This is destructive and unrecoverable.
Skill Claude CodeCodex
When to use: The user wants to open the reflexio web UI to manage skills/preferences.
Skill Claude CodeCodex
When to use: The user wants immediate extraction of skills/preferences from the current session — e.g., after a major correction, before context compaction, or to test the loop.
Skill Claude CodeCodex
When to use: Always active. This skill is the contract between you and the reflexio cross-session memory plugin.
Skill Claude CodeCodex
When to use: The user is hitting "reflexio unreachable" errors or wants to restart the local backend cleanly.
Skill Claude CodeCodex
When to use: The user wants to see what reflexio currently knows about this project.
Skill Codex
Integrate Reflexio Enterprise into an existing AI agent application — retrieve learned context before the agent acts, and ingest interactions by direct publishing or by connecting existing supported tracing. Use when a developer asks to add, install, wire, verify, or evaluate Reflexio in an agent codebase; not for…
Skill Claude CodeCodex
Connect Braintrust, Langfuse, LangSmith, Phoenix Cloud, or OpenTelemetry traces to Reflexio through its setup APIs. Guide the agent developer through traffic selection and field mapping, save and validate a draft, and return the Reflexio review link for frontend activation. Do not add an interaction-publish flow.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: