Self Evolving Agents

Orkas is an open-source (MIT), local-first AI team for your desktop: a Commander turns your goal into to-dos and coordinates 16 built-in specialist agents plus Claude Code, Codex, OpenCode, OpenClaw and Hermes, with projects, scheduled automations and connectors. Free app for macOS & Windows; built-in models or your own keys.

Self-hosted Enterprise and Personal AI + agent runtime in .NET (NativeAOT-friendly)

Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi-agent evolution. Accepted at COLM 2026.

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

Open-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no target-task supervision. (Code coming soon.)

Harness self-evolution: update targets, theory, evaluation, and reported evidence. Bilingual reading list and project website.

VibeGame: Vibe Your Dream Game -- An open-source self-evolving multi-agent framework with an AI-Native game engine that turns your natural language into a fully playable 2D web game and edit it any way you want, built on Claude Code & Codex.

A curated list of AI Agent evolution, memory systems, multi-agent architectures, and self-improvement projects. | evomap.ai

Mojito — the local, evolving alternative to cloud personal AI like Meta Muse.

Run Hermes Agent - a self-evolving AI assistant - on any Android device using Termux. One-line installation.

The agent OS that evolves itself. 51 workers, 18 security layers, self-improving functions. Built on iii-engine.

Enterprise-grade, local-first Agent Workbench for people and agent teams. A unified multi-engine workspace for Codex Harness, DeepSeek Harness, and OpenCode, with unified plugins and Skills, multi-agent projects and tasks, and editable code, documents, presentations, design, and video.

Human directs. AI delivers.

Agent memory: long-term memory & agent memory handoff. Claude Code & Codex.

PocketStrike is a privacy-first mobile AI workstation. It combines zero-cloud native on-device GGUF inference (ARM NEON accelerated) │ with frontier cloud LLMs, multi-step ReAct agent tools, Model Context Protocol (MCP) servers, self-evolving cross-session memory, and FLUX neural image │ generation.

Self-evolving cognitive memory and context engine for AI agents in Java. Empowering 24/7 proactive agents like OpenClaw with understanding and SOTA performance.

Verifiable program-level self-evolution for AI-for-Science agents: Skills and typed Operators grow from replay-verified executions.

Self-evolving browser automation for Codex, Claude Code, and Cursor—learn reusable site knowledge and safely replay verified routines with agent-browser.

Fully Autonomous AI Research System with Self-Evolution, built natively on Claude Code

🐧 Unified and Stable RSI Platform

Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Active Hybrid GraphRAG, DreamService, and self-healing loops.

Local-first AI agent workbench for long-running projects: background work, built-in memory (no Docker), six web search services, MCP. macOS, Linux, Windows.

EvoOntology: A Self-Evolving Ontology Layer for Data Agents ⚙️ EvoOntology插件为Claude Code/Codex 建立&进化本体层

A self-evolved, sovereign desktop AI agent built for real-world action — beyond model wrappers and coding copilots. / 真实实践中自我演化的独立桌面 AI Agent。

The first self-evolving AI agent. Rewrites its own source code in real-time. 6 AST mutation strategies. Absorbs GitHub repos autonomously. 7 autonomic drives. Standalone CLI. Works anywhere.

Give your AI a life — open-source infrastructure for persistent, self-maintaining AI companions. Powered by Claude Code.

🔬 Harness Vibe Research with Self-evolving AI Scientists

Open-source personal AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent, multi-model, multi-channel. Lightweight, extensible, one-line install.