Autonomous AI agents that perform tasks independently
Meko1
大模型面试指南
omohikane
🌑 SAKU (朔) — A self-evolving local AI agent with persistent personality and Markdown memory
Drop-in tamper-evident audit callbacks for LangChain, LangGraph, CrewAI, AutoGen, PydanticAI. Streams events into the Ujex hash-chained audit ledger (IETF draft-sharif-agent-audit-trail-00).
...moreagentkit-js contributors
Drop agentkit-js sandbox kernels into the OpenAI Agents JS SDK as a Tool — edge-safe code execution with one capability manifest, no E2B sandbox needed
...moreStellars Henson <[email protected]>
Project that uses theory of From Word Embeddings To Document Distances / Optimal Transport to give meaningful distance from one document to another, useful if building agentic projects that convert or extract information from one document to another using frontier models but without the ability to calculate KL divergence from logits
...morexQUANTUMTECH
Lightweight model-agnostic cognitive agent engine (TypeScript). Planning, task decomposition, context management & tool-discipline over any OpenAI-compatible model.
...moreOfficial Python SDK for Ujex Postbox — email-for-AI-agents with built-in prompt-injection scoring, auth verdicts, and plus-addressed task threading.
...moretnezdev
Local runtime package for Agentic workspaces
Travis Nesland
Executable toolbelt for agent self-improvement
zhaofilms
One-command installer for the official notionx AI agent skill (Claude Code, Trae IDE, OpenAI Codex).
zxz106220
Install an AI agent skill for writing clear, testable technical product requirements across Codex, Claude Code, Cursor, Gemini CLI, OpenCode, OpenClaw, Hermes Agent, CodeBuddy, GitHub Copilot, and Trae.
...morebacnh85
Manage repository-based AI agent skills from git and local sources.
jnmetacode
Local-first DevTools for AI agents. See every tool call, prompt, and token — 100% on your machine. Zero cloud, zero signup, one command.
...moresamuelchien821
Detect failures, investigate root causes, and hill-climb fixes for AI agents. Uses your Claude Code subscription.
GitHub Actions
Goal-driven code development pipelines for coding agents, built on coding-agent-forge.
GitHub Actions
Local codebase intelligence server for coding agents — type-aware repo maps + semantic code search via Ollama. Pluggable into any agent via HTTP.
...morepostsiva
AI Agent & Workflow System - Use specialized AI agents with Claude, Cursor, or any AI tool
maxime-useago
Create In-APP AI agents that answers question and performs actions. Works with React, Vue, Angular and vanilla JS/TS.
miosa-osa
Filesystem-first framework for MIOSA OSA Projects.
yorukid
Open-source terminal AI agent for coding, deep research, automation, and multi-platform task execution.
akshaylakkur
Qode — Autonomous Coding Agent. Full-stack AI coding agent for your terminal. Includes QSSH remote execution.
akshaylakkur
Qode — Autonomous Coding Agent. Full-stack AI coding agent for your terminal. Includes QSSH remote execution.
beamuswayne
Alfred — a verifiable autonomous coding agent (CLI). Machine-enforced done-gates, agent-curated inspectable memory, signed replayable run ledgers. TypeScript on Bun.
...moresourrris
Standardized AI agent environment profiles, quality gates, security policies, and memory contracts for Cursor, Claude Code, Codex, Gemini / Antigravity, OpenCode, and GitHub Copilot.
...more