Malleable coding agent app. Use Claude Code and Codex to code and reshape the app itself live.
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.
Self-replicating, self-modifying Assembly program that can evolve into every possible computer program in the universe (EXPERIMENTAL)
Self-aware cognitive AI agent that reads, modifies & verifies its own code. Autonomous planning, episodic memory, emotional state & MCP integration. Runs on Claude, GPT-4 or Ollama. Electron desktop app for Windows, macOS & Linux.
multi-headed intelligence for modern AI - a clojure agent system with dynamic tools and llm delegation
一个支持自修改的 C++规则执行器虚拟机，支持动态修改指令和规则间调用
An unprompted Claude agent that reads its own code, modifies its own code, and writes notes to its next-turn self. Brain-inspired architecture (cerebellum/amygdala/dopamine/etc). Git log is its fossil record. | 一个不被预设动机的 Claude agent，仿生大脑架构，git log 是它的化石。
GENESIS PHASE — Self-creating AI agent with genuine learning. Based on Ouroboros by razzant. 8 behavior-changing upgrades, 6 bug fixes from senior code review. Setup wizard included.
Aurogene - self-evolving digital mind
SMAGo — Self-Modifying AI Agent
Spelunking the depths of self-reproducing programs. My favorite so far is the Frankenquine.
EVA - a minimal self-evolving agent that safely rewrites, tests, and promotes better versions of itself inside a hardened Docker sandbox.
Ein datengetriebenes, vollgrafisches Anno-Style-Aufbauspiel, das sich jede Nacht von einer lokalen KI (Gemma via llama.cpp) selbst erweitert — mit voller Transparenz, Rollback und Sicherheits-Wächtern.
VIKO — Personal AI voice assistant with Gemini Live API, speaker verification, futuristic HUD, and self-modification capabilities
⚡ A lean, local-first, self-modifying AI agent framework. Pi-compatible skills. Zero-trust sandbox. One model, no bloat.
An AI agent that starts empty and writes its own tools
Autonomous agent that rewrites its own source code, with three local LLMs deliberating on every change. Runs on Ollama, persists across crashes, pushes its own commits. Successor to Ecnyss.
A self-evolving autonomous system built entirely by minimax's delegate chain — every 7 minutes it reads its own source, decides what to build next, and rewrites itself. No human writes code here.
A self-modifying operating system for an autonomous agent - the LLM is the CPU. Persistent processes, a priority scheduler (single or multi-core), a knowledge base, and gated self-evolution (build in a worktree, verify, promote, re-exec).
Add a description, image, and links to the self-modifying topic page so that developers can more easily learn about it.
To associate your repository with the self-modifying topic, visit your repo's landing page and select "manage topics."