Reflexio: self-improving agents that learn from corrections, no retraining
Learning platform that converts user corrections and failed execution paths into 'playbooks' - agents adjust behavior and logic at runtime instead of waiting for a fine-tune.
Why it matters
Goes beyond memory-as-retrieval: a two-stage pipeline clusters individual user playbooks into cross-user agent playbooks, so one user's correction improves every user's agent.
What you could build with it
Route support or coding agents through Reflexio so human corrections become reusable playbook rules instead of one-off fixes.
First spotted on engineering blog: source.
More AI agents
hermes-agent (NousResearch)Self-improving personal AI agent across Telegram, Discord, Slack, and terminal with persistent memory.agents · JEV 0.73Paperclip: the app people use to manage agents at workOpen-source orchestration for teams of AI agents: org charts, budgets, governance, heartbeats and a ticket system in…agents · JEV 0.73AIHOT — open-source framework for building automated industry-news sitesFull-stack framework (Node 24 + PostgreSQL) that ingests RSS/webpages/X/WeChat, dedupes, double-scores, clusters with…agents · JEV 0.73orcaAgent development environment for working with a fleet of parallel agents on your own subscription.agents · JEV 0.68Univer 1.0: Office Harness for AI AgentsUniver 1.0 unifies six editors (Sheets, Docs, Slides, Boards, Bases, PDFs) into one programmable, embeddable Office…agents · JEV 0.68Nasiko: developer control plane for AI agentsRust control plane giving developers one dashboard to deploy, monitor, and govern fleets of AI agents.agents · JEV 0.68
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.