Autonomous AI agents that perform tasks independently
heichaowo
A-MEM memory plugin for OpenClaw — memories evolve, not just accumulate. Graph linking, hybrid retrieval & LLM evolution judgment.
...moreAn AI SOC kernel: an event-sourced, multi-agent SOC where a role-based team of LLM agents works a case over a shared event bus — with case memory, human-in-the-loop gating, and a replayable audit log. Bring your own LLM, alert source, and tools.
...moreRESK Security
Agent Action Logging Platform — log all AI/LLM agent actions to any platform
rickblalock
Omakase — the chef's standard. Portable senior-craftsmanship skill (markdown-first) + npx omakaseagent skills install for Cursor/Claude/Agents. Enforces 12 Rules + Critique Rubric. Zero slop.
...moreikoikoiko
Local, explainable skill router for Codex and agent skills.
bilibieber
The Mandate Agent SDK — Trust Engine for the Agent Economy
cybernandan
Many agents. One runtime. Separate lives. Run distinct local AI agents — each with its own soul, memory, secrets, skills, workspace, and autonomy level.
...morevyom-patel
AI-powered CLI to scaffold any project — React, Next.js, Vue, RN, FastAPI, Django & more
GitHub Actions
Atrium — public, self-hostable, Convex-backed web chat UI for AI agent gateways (OpenClaw today, Hermes next). Ships an origin-agnostic static bundle (Convex URL injected at runtime via /config.json).
...morejosharsh
A minimal browser-agent harness - six tools, any model. pi for the browser.
ele-yufo
Standalone zero-dependency CLI for xAI Grok via SuperGrok / X Premium+ OAuth — chat, search, image, video, TTS, transcription. No API key, no pip install.
...morejune lee
Read once, never again — self-describing files so AI agents stop re-parsing.
AISTV
AISTV - AI IT Agent cho Windows
mathiasdangl
VibeStudio — dein lokaler Vibing-Agent. Beschreibe deine Idee, VibeStudio übernimmt Architektur, Versionskontrolle und Hosting.
...moreqiushu-wq
Multi-Agent Context Quota Manager + Diagnostic Tool — 40 lines, zero dependencies
Echo Agent contributors
A self-hosted, long-running AI agent runtime with memory, skills, plugins, and multi-channel integrations
Local-first multi-agent coordination bus: work claims, presence, chat, and resource sharing over a WebSocket hub
saagpatel
Query your own Claude Code agent history with DuckDB, read-only, straight over the JSONL transcripts.
AI-XiaoDao
Windows MCP browser automation — 217 tools · Cursor/Claude/Cline · web scraping · POST reverse · CDP debugger · Playwright alternative · FBrowser CEF · x64+win32 · MIT open source · Download & run
...moreLen4m
Boot a real x86 Alpine Linux VM in your browser (v86), attach xterm consoles, and let a local AI agent run tools inside the guest—Transformers.js/Ollama, static SPA, no cloud VM required.
...mores3onghyun
The soul of a DevOps/Platform consultant — an agent persona (values, voice, judgment) for GitLab CI/CD, Observability, and Kubernetes. Evidence-first, honest, asks for the right tool.
...moremasa-san-jp
アイコ人格を Codex / Claude Code などのエージェントで実行・育成・切替するためのプロジェクト / Persona-driven AI agent framework for running and customizing Aiko across Codex and Claude Code.
...moreLyx3314844-03
超级爬虫智能体 — 自进化AI爬虫系统｜四原生引擎(Go/Python/Java/Rust)｜JS逆向(AST反混淆·Hook注入·签名追踪·WASM解析)｜六阶段进化闭环(规划·批判·执行·自修复·进化·反思)｜自适应反检测·指纹轮换·行为模拟｜遗传算法策略优化｜知识图谱·群体协调｜LLM选择器自愈·代码合成｜跨域策略迁移｜Docker/K8s部署
...moreA lightweight multi-agent framework built on top of pydantic-ai.