Autonomous AI agents that perform tasks independently
purposewalks
Declarative AI task orchestration hook with streaming, tool calling, human-in-the-loop, fallback, and cost tracking
cardinals-org
GouGouBi prediction market agent SDK — skill definitions, capability catalog, prompt builders, and contract constants for building AI agents that interact with decentralized prediction markets on BNB Chain.
...moreLLM-driven agent for describing data tables based on domain schemas
longyunfeigu
A 27-chapter hands-on tutorial for building an autonomous AI agent from zero in Python. Agent loop, tool system, memory, skills, MCP, multi-platform gateway, and self-evolution — inspired by Hermes Agent.
...moreEmersonBraun
The complete toolkit for building AI agents in JavaScript. Lightweight core, React & Terminal UIs, autonomous runtime, tools, skills, memory, RAG and observability. Plug-and-play from chat UI to full agents.
...morejosephnhtam
DeepAgentNet is an agent harness for .NET — a ready-to-run framework for building autonomous agents. Instead of wiring up prompts, tools, and context management yourself, you get a working agent out of the box and customize what you need.
...moreeikarna
A high-performance Rust implementation of the Hermes-Agent orchestration loop for LLM-driven tool execution.
hrabanazviking
Super-advanced agentic AI framework for cyber-Vikings. Birth autonomous, self-evolving thoughtforms that manifest as hyper-realistic 3D digital characters. Features persistent memory, ritual invocations, full VR/Unity integration, and gloriously unaligned intelligence. Pure modernist cyber-Heathenry — no gatekeeping, pure emergence. 🔥⚔️🤖
...morequalixar
Qualixar OS: The Universal OS for AI Agents. Claw-compatible. 12 topologies, Forge AI team designer, 24-tab dashboard, skill marketplace. PAPER: https://arxiv.org/abs/2604.06392
...moreintelligexhq
Chronos is visual AI agent builder - tailored for self-hosted deployments and observability
SuperSwinkAI
An extensible, policy-minded agent harness in pure Rust. Any LLM via one trait. Concurrent tools, policy guardrails, session memory, eval harness, and TUI included.
...morepromptshieldhq
A free, open-source LLM security proxy. Drop it between your app and any LLM provider to get rate limiting, audit logging, token tracking, and Prometheus metrics with no code changes to your app.
...moreJoeStrout
LLM-based agent for in-depth photo/image manipulation
ShamsRupak
SAGE: Self-Adaptive Goal-directed Executor — A multi-tool LLM agent with DAG-based hierarchical planning, ReAct reasoning, and evidence-guided self-correction for automated research synthesis. Built from scratch, no frameworks.
...moreArpandeep Khatua, Hao Zhu, Peter Tran, Arya Prabhudesai, Frederic Sadrieh, Johann K. Lieberwirth, Xinkai Yu, Yicheng Fu, Michael J. Ryan, Jiaxin Pei, Diyi Yang
Multi-agent coordination benchmark for collaborative code generation
fwHanHacker
基于 Agent 的服务自动化修复系统
Varun Pratap Bhardwaj
Formal behavioral specification and runtime enforcement for autonomous AI agents. Agent Behavioral Contracts (ABC).
Varun Pratap Bhardwaj <[email protected]>
Formal regression testing for non-deterministic AI agent workflows
Scan your Claude Code setup for behavioral discipline gaps vs. production-grade patterns. Get a scored report with copy-paste fixes.
...moreBuild interactive demo files for exploring code changes. A CLI tool designed to be used by AI agents — the --help text is the only documentation needed. Produces cell-based percent-format scripts that users step through interactively in their editor. Inspired by Showboat (LLM-as-user CLI design), Solveit (exploratory dialog over code dumps), and jupytext.nvim (plain .py files, no notebook JSON).
...morerhinehart514
A product engineering brain for Claude Code. 28 skills and 7 agents that make Claude think like a co-founder — walk the product, grill the frame, name real users, kill the weakest feature, write the launch post. Runs locally, no SaaS.
...moreohmygodnxd914
Reliability and observability SDK for AI agent operators
breakthroughcoachingai
Clementine — Personal AI Assistant (TypeScript)
GitHub Actions
Pull AI agent configurations (Cursor, Copilot, Claude, Windsurf, Antigravity, Aider) from any git host — tracked, verified, updatable
...more