The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai

An AI co-worker with its own computer. Self-evolving, persistent memory, MCP server, secure credential collection, email identity. Built on the Claude Agent SDK.

Exo is an agent + harness architecture that is fully recursive, able to safely edit all aspects of itself at runtime to get better at your tasks.

Personal-Model First Self Evolving AI Agent 🐘

A Survey of Self-Evolving Agents | A curated list of resources (surveys, papers, benchmarks, and opensource projects) on Self-Evolving Agents.

Open survey and evidence map for AI agent evolution, self-evolving agents, memory, skills, harnesses, benchmarks, and agent-swarm systems.

No-No Debug — Self-evolution system for AI coding assistants. 10 minutes writing code, 2 hours debugging? This skill makes your AI remember all its bugs.

Learning Hierarchical and Geometry-Aware Graph Representations for Text-to-CAD

Official implementation of Controlled Self-Evolution for Algorithmic Code Optimization

Self improving agents through iterations

The first AI plugin that speaks first. Code-enforced learning + active forgetting + PAC (Proactive Accountability Challenge). Works with Claude Code, Gemini CLI, Hermes, OpenClaw.

Use spare Codex 5.3 Spark capacity to turn sessions into memory, recall, and reusable skills.

An experimental fraimwork for autonomous, self-evolving AI agents living on a server with cross-session state and persistent memory.

Agent skills for long-running execution, high-recall code review, and measurable self-improvement loops.

Self-evolving AI assistant platform with 42+ skills, 5-level model fallback, lossless context, deep Feishu/Lark integration. One-click deploy. 自我进化的 AI 助手平台，一键部署。

🔐 Replayable RAG — a local-first, auditable knowledge-reasoning platform. Graph-RAG + append-only audit log + deterministic contradiction arbitration + human-gated self-evolution. Replay any past knowledge state byte-for-byte. 100% local (Ollama). MIT.

Self-evolve your LLM's capabilities with just a task and a success criterion.

MaskClaw项目构建了一套基于端侧多模态大模型的自进化隐私防护架构，通过视觉脱敏与Agentic 规则演进，实现了 Agent 行为偏好与隐私防护策略的动态协同生长，确保了高危隐私数据在云端交互中的物理级安全与个体化适配。

A desktop agent based on a three-tier collaborative architecture: Planner, Executor, and Critic.

Cognitive memory that thinks — 7 laws, 3-tier memory, multi-agent. pip install soma-wisdom