Autonomous AI agents that perform tasks independently
MatterLoop Contributors
Model agents and DAG-based multi-agent collaboration components for MatterLoop
fractaal
Directive-root loading and mid-turn discovery for Pi across CLAUDE.md, AGENTS.md, MEMORY.md, and shared skill directories.
...moreMatheus Eduardo
Permission, human-confirmation and audit-log guardrails for LLM tool calling.
al4xdev
Typed async map/consolidate/reduce orchestration for LLM applications
DinoMem
DinoMem integration for CrewAI — drop-in memory tools for any Crew agent
Cheng Yuanqi <[email protected]>
LeAgent — Intelligent Office Agent Platform
Shashank Singh <[email protected]>
A progressive framework for building agentic AI systems with Google Gemini.
pexuleco
n8n community node for the Digisac API: contacts, tickets, messages, campaigns, services, departments, users, tags, schedules, webhooks, reports and every documented Postman endpoint. Usable as an AI Agent tool.
...morenetopsengineer
Optimize a Claude Code / Agent skill's description frontmatter for reliable triggering — no API key required.
Agastya Choudhary <[email protected]>
Train and serve LLMs on any hardware with one command each
jishen
Explicit upstream-exact Superpowers host mode for Agentic with lazy ECC domain knowledge.
ch1nyzzz
Unified LLM API with automatic model discovery and provider configuration
Rudrendu Paul, Sourav Nandy
Compare AI coding tool spend before and after a migration -- Cursor vs Claude Code, real numbers pulled from each vendor's own admin API, one command, zero runtime dependencies.
...moreopen-multi-agent
Optional OpenTelemetry adapter for @open-multi-agent/core TraceRecord v2.
TealTiger Team <[email protected]>
Export TealTiger governance decisions as OpenTelemetry spans in Arize Phoenix LLM trace viewer.
bntvllnt
General-purpose agent with transport abstraction, state management, and attachment support
NVIDIA Corporation
LangChain Deep Agents adapter for NeMo Fabric
Sergey Kostenchuk
Production-ready hybrid knowledge base combining a governed Markdown Wiki with deterministic local RAG.
Adhithya Karthikeyan <[email protected]>
A lightweight, personal Claude Code-style agentic CLI for LOCAL LLMs (LM Studio).
lovesworking
One timeline across every Buoy devtool, with LLM-ready export presets. Part of Buoy devtools.
GitHub Actions
The lightweight, AI-native self-hosted knowledge base — built-in RAG, hybrid semantic search, and a clean REST API for AI agents.
...moreBruce-Arhin Shadrach <[email protected]>
A lightweight LLM agent framework with standard and structured tool support use, prompt management, and support for OpenAI.
...moreRudrendu Paul, Sourav Nandy
Regression-testing CI gate for self-edited Claude Agent Skills (SKILL.md, MEMORY.md): golden-transcript record/replay against a skill's own declared and inferred capability surface, zero hosted infrastructure.
...morejishen
Explicit upstream-exact Superpowers host mode for Agentic with lazy ECC domain knowledge.