Autonomous AI agents that perform tasks independently
Semantic LLM response caching — stop paying for the same call twice.
yuzhouzhou
Diagnostic and governance CLI for AI agent skills
wasmagent contributors
Drop wasmagent sandbox kernels into the OpenAI Agents JS SDK as a Tool — edge-safe code execution with one capability manifest, no E2B sandbox needed
...morevishwaksen-1
CI-native documentation layer for RTL projects
A permission gate for AI agent tool calls. Stops dangerous actions before they execute. Safe under many concurrent agents.
...moreJuan Lavieri
A foundational knowledge layer for AI: a context-rich catalog of any document store plus an agentic hybrid retriever. Plug-and-play, zero required dependencies.
...moreagent-phonon contributors
Server SDK for agent-phonon — orchestrate AI agents across multiple devices.
The Universal Looping AI Orchestrator — a runtime-agnostic super-plugin (6 skills) that drains any queue of work end-to-end on any LLM/runtime.
...morekjoshi
ForgeSight LangGraph adapter — auto-instrument LangGraph/LangChain agents via callbacks.
Abdulsamet Atas
Deterministic, no-LLM tool-call guardrail for Strands agents, backed by the rein engine.
rami8612
TypeScript SDK for operating a BVCC Agent Wallet from an off-chain AI agent. On-chain spending limits, no private-key custody by BVCC.
...moreKasishStar
Tool-use agent with optional LLM brain via Ollama. Pure Python stdlib.
Open-source intelligent model router and multi-agent orchestrator. The open alternative to Sakana AI's Fugu.
Julian Geymonat
Deterministic, token-minimal, reproducible memory for Claude and agents: wikilink-graph retrieval, then compaction, then a Claude reader.
...morehe-yufeng
CI-grade evidence and safety tools for AI agents, MCP servers, and open-source work — one CLI: ci-repro, patch-context, mcp-gate, mcp-replay, tool-fence.
...moreParth3930
Private, offline-first local AI agent & developer assistant. Runs embedded llama.cpp (GGUF) entirely on-device with WhatsApp, Discord, and terminal CLI tools.
...morealiyun
Official Alibaba Cloud MCP servers, skills, and plugins to help AI agents build on Alibaba Cloud
rejigtian
AI-driven Android UI test automation — plain-language cases run by an agent on real devices over any network (no ADB/scripts), with visual reports & self-learning.
...moreMirkomil Sharipov
FERNme — a user-owned, near-zero-LLM memory layer for AI agents (websites today; desktop and mobile on the roadmap).
Abdul Basit
Job search automation with LLM API pipeline mode and Claude Code agent mode.
Rajan Patel
Install AGENTS.md and .agents/ configuration for Canonical Workshop projects
Production reliability suite for LangChain/LangGraph multi-agent systems
LLM based Literature Search Agent
Weave: composable AI agents with a universal interface. Connect any framework (LangChain, CrewAI, or any Python callable) with no rewrite.
...more