Autonomous AI agents that perform tasks independently
dotdev <[email protected]>
Multi-session voice web interface for AI coding agents
Human-reviewed Agent DAG framework
ToPo
An AI Operating System for local LLMs — register apps, and let AI agents use them.
SuperMarioYL
Per-provider tool-call contract regression sentinel for Chinese LLMs (DeepSeek/Qwen/Kimi/GLM/MiniMax).
Benchmark 20 agent-memory strategies (Mem0, Graphiti, Graphiti-on-FalkorDB, Cognee, LangMem, Memori, Karpathy LLM Wiki, A-MEM, HippoRAG 2, quantum rerankers, plus pure-Python baselines and advanced retrievers) on the same evaluator under the same configs
...morePlain-English -> verified CUDA kernels via Claude-driven agent loop
nczz
Discord control plane for project-bound ACP agents. Kiro CLI by default, optional OMP, MCP policy, audit, usage, cron, and thread agents.
...morezlatko-lakisic
Model-agnostic multi-agent orchestration built on CrewAI. YAML-driven agent and MCP catalogs, dynamic LLM planning, sessions, and pluggable execution — mix Ollama, OpenAI, Anthropic, HuggingFace, and your own tools without rewriting orchestration logic.
...moretjdrhs90
Idea-to-store harness for Flutter/Flame games
Universal Evidence-Grounded Multi-Agent Deliberation Layer for any encoder
pkhunachak
Autonomous diagnostic agent for Kinetica databases
bennhuang
Meta Ads CLI for AI agents
dstwn
A fork of agentmap adding PHP/Laravel support — the repo map your coding agent is forced to use. Estimated ~98% fewer context tokens to understand a PHP/Laravel or TS/JS codebase. A queryable, ranked code-relationship map (tree-sitter-php + ts-morph): Pag
...moreShrink AI-agent command output to save tokens (git + npm, Windows)
SpanoAI
Python SDK for SpanoAI — shared working memory + a message bus for multi-agent AI systems
Adaptive Information-Aware Chunking for RAG and Agentic Systems, driven by information density instead of fixed token counts.
...moreSmall metadata and URL helpers for AI Agent Skills, a curated Claude, Codex, and AI agent skills directory.
yuanchenglu
从零构建的 LLM Agent Harness 实践项目——Agent Loop、Tool Use、Context Engineering、Memory
shamspias
A lightweight agent harness you bolt onto your app so an LLM can operate it — safely, and cheaply.
tianshanghong
🚦 Status board & notifications for Claude Code and Codex — glance at an iPad (or get a desktop alert) when an AI coding agent needs you, finishes, or gets stuck. Self-hosted, zero dependencies.
...morezhengjie9510
Docker sandbox backend for AI agents - execute code safely in isolated containers
Build, trace, inspect, and replay AI workflows with pluggable instrumentation and storage backends.
oxbshw
The Web Access Gateway for AI Agents — 52 channels, 92 MCP tools, 9 SDKs, self-healing backends, async Rust
amitpatole
Verified agents — nothing is "done" until a grader returns a verdict. Eyes (AgentVision) + verdict bus + compounding memory + a fleet + agent-built tooling + agent-run CI/CD.
...more