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.
-
Updated
Sep 25, 2026 - Python
#
self-improving-agent
Here are 45 public repositories matching this topic...
An end-to-end agent project for GPU kernel implementation, analysis, profiling, and iterative optimization. It helps an agent turn PyTorch logic or an existing kernel into a high-performance GPU kernel through a structured, profile-driven workflow.
agent skills gpu nvidia-gpu gpu-programming amd-gpu agentic-workflow self-improving-agent gpu-kernel autoresearch kernel-generation
-
Updated
Sep 23, 2026 - Python
A selective learning and memory substrate for agentic systems — typed, revisable, decayable memory with competence learning and trust-aware retrieval.
agent learning collaborate knowledge-management autonomous-agents ai-agents rag agent-framework llm agentic agent-skills agent-memory self-improving-ai self-improving-agent openclaw revisable-knowledge openclaw-plugin openclaw-memory
-
Updated
Sep 5, 2026 - Go
Persistent local memory for AI coding agents — Claude Code, Codex CLI, Cursor, any MCP client. Temporal knowledge graph, procedural memory, AST codebase ingest, cross-project analogy. LongMemEval R@5 95.1%, LoCoMo 0.607, BEAM 1M 0.448. 74 MCP tools, 9 IDEs, 100% local.
python sqlite mcp knowledge-graph developer-tools persistent-memory semantic-search knowledge-management rag llm-tools ai-memory model-context-protocol mcp-server agent-memory claude-code codex-cli self-improving-agent claude-code-mcp claude-code-plugin claude-memory
-
Updated
Sep 24, 2026 - Python
Self-improvement loop for Hermes Agent: reads its own trajectory, proposes and applies the smallest skill/memory edit (create/patch), journaled with rollback. /refine command, refine_run tool, on_session_end hook.
-
Updated
Sep 25, 2026 - Python
Official implementation of Continual Harness (arxiv.org/abs/2605.09998) on ARC-AGI-3
-
Updated
Jul 3, 2026 - Python
Open-source, self-hosted AI agent that evolves its own code to perform better in your specific use-cases.
open-source autonomous-agents ai-agents ai-agent llms agentic-ai coding-agent self-improving-agent deep-agents workflow-automation-ai self-modifying-ai self-evolving-agent
-
Updated
Sep 3, 2026 - Python
Browser-native agent · profiles · tools — by aratech | Zero installs, isolated, secured and self-evolving agent.
-
Updated
May 31, 2026 - TypeScript
Self-improving agents, governed. Areev is the substrate for adaptive agents — agents that get better from their own history, under human authority, in steps you can inspect, undo, and re-measure.
rust memory mcp adaptive-learning embedded-database self-improvement ai-agents self-improving adaptive-agents llm adaptive-ai agent-memory self-improving-ai self-improving-agent self-improving-systems self-improving-agents
-
Updated
Sep 25, 2026 - Rust
[COLM-LLA 2026] The official implementation for paper "AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation"
-
Updated
Aug 23, 2026 - Python
An autonomous content marketing team. Talk to your agents on Telegram. Always on. Auto-improving.
multi-agent content-marketing autonomous-agents ai-agents claude self-improving-ai self-improving-agent telegram-bot-ai-assistant
-
Updated
Mar 25, 2026 - HTML
A self-hosted AI agent that thinks, acts, and improves itself – all running privately on your own machine. Browses the web, writes and executes code, manages files, sends emails, monitors URLs, builds websites, and learns from every interaction.
automation ai ai-agents own-your-data ai-assistant ai-tools localagent agentic-workflow agent-skills self-improving-agent persistant-memory
-
Updated
Aug 30, 2026 - Python
Learn to build recursive self improvement agents
-
Updated
Aug 3, 2026 - HTML
Open-source search engine that automatically evolves your AI agent's prompts, tools, and harness logic through iterative evaluation — plug in Claude Code, Codex, Hermes, or any CLI agent.
-
Updated
Jul 3, 2026 - Python
An OpenClaw skill that upgrades self-improving agents from reactive error logging to goal-driven capability evolution with curriculum, evaluation, transfer, and promotion.
-
Updated
Mar 31, 2026 - Python
A self-improving ML agent that compounds capability across projects through knowledge crystallization, reusable skills and shared ML/MLOps infrastructure.
ai-agents mlops ml-experiments agent-skills agent-memory self-improving-agent organizational-learning knowledge-crystallization native-ai
-
Updated
Aug 28, 2026 - Python
A self-improving Agent that utilizes AI to generate, validate, and execute MATLAB simulations.
-
Updated
May 22, 2025 - Python
AI Research Radar — Evidence-Grounded Trend Ledger for AI Systems
ai skills memory ai-agents claude ai-agent ai-memory agent-memory self-improving-ai self-improving-agent claude-skills loop-engineering
-
Updated
Sep 25, 2026
AI Security Research Radar — AI for security and security for AI
ai memory jailbreak red-team ai-agents claude ai-security ai-agent ai-red-team llm-security ai-memory ai-jailbreak agent-memory self-improving-ai llm-injection mcp-security self-improving-agent claude-skills skills-security loop-engineering
-
Updated
Sep 25, 2026
Speak. She becomes yours.
voice assistant copilot grok assistant-chat-bots self-improving copilot-enabled self-improving-ai self-improving-agent copilot-coding-agent self-improving-agents
-
Updated
Sep 7, 2026 - TypeScript
Add this topic to your repo
To associate your repository with the self-improving-agent topic, visit your repo's landing page and select "manage topics."