Autonomous AI agents that perform tasks independently
OSCAR Team
OSCAR - GitHub-Specialized AI Coding Assistant (multi-provider: Gemini, OpenAI, Claude, Groq, Ollama)
Routing + ingress + observability hub for Claude Agent SDK agents you self-host.
777genius
You're the CTO, agents are your team. They handle tasks on their own, message each other, and review each other's work. You just watch the kanban board and give high-level commands. Codex/Claude/OpenCode(200+ models, 75+ LLM providers, free models no auth). Build your AI company.
...moreSynapCores
Real, framework-free AI support agent where SynapCores is the brain — memory, RAG, tool routing, generation in one database. Browser chat widget + live Brain debug sidebar. Fork and run in 30s.
...morenowa277
MinerU-powered academic paper analysis tool for AI agents
wjgong001
AI toolkit for Termux — real scripts, configs, and docs for running AI agents on Android phones. From zero to a surviving AI: whisper.cpp, voice transcription, GitHub workflows, and environment bootstrapping.
...morestwilliam503388-creator
AI Agent PM 12周完整学习项目 - 84篇笔记+6个实战项目+全套考试系统+面试策略
xiaojilele-glitch
AI Agent OS with visible workflow, real execution, and a 3D office shell. From one sentence to full task lifecycle — plan, run, review, replay.
...moregryszzz
Unified AI execution runtime / framework & sandbox for coding agents across CLI, VS Code, terminal, and web surfaces. Rust frame work, programmable capabilites.
...moreEliyce
Spec-driven development framework — AI agents that think before they type
jkraybill
Multi-model adversarial review for catching shared blind spots
ai-zona
AIZona Agent Development Kit — Build governed AI agent teams with TypeScript. MIT Licensed.
actinon-com
Agentic AI for Odoo 18
developer1ab
Built for true mobile autonomy: local Android control, real-time screen understanding, and step-by-step task execution across system intents and third-party apps.
...morezhengyang-2002
Nighttime ML experiment workflow with Claude Code multi-agent orchestration (Planner / Executor / Reviewer / Auditor)
hinanohart
Reliability-science metrics for repeated-attempt evaluation of long-horizon LLM agents: pass@k, pass^k, Bayesian posteriors, RDC/VAF/GDS/MOP.
...moreStore agent conversation logs (e.g. Claude Code JSONL) as HDF5 for cheaper context reconstruction, analytical queries, and self-contained provenance.
...moreGitHub Actions
Install the PingCode Codex skill with npx.
keyreyla
Unified LLM API with automatic model discovery and provider configuration
rubenglez
Locale-aware eval harness for AI agent behavior
haruhunab1320
Git workspace provisioning and credential management service with OAuth device flow authentication
makshc2
Curated AI agent skills for Vue 3 + Vite development — works with Cursor, Amp, and Claude Code.
cosmo-wise
Harness CLI for long-running AI agent tasks
oc-xiaoju
Agent framework — `createAgent` factory, context builder, frontmatter fast-path, and LLM extract pipeline.