Autonomous AI agents that perform tasks independently
Stigmergic Contributors
A near-zero-dependency, fault-tolerant multi-agent framework built on Stigmergy, Latent State Transfer, and a Byzantine-inspired consensus quorum.
...moreZierhut IT, Alexander Zierhut
Shared chassis for agent-ready CLIs: the exit-code contract, JSON/table/markdown/CSV output with field projection, and keyring-backed credentials.
...moreHolokai
SDK for building Holokai neurons in Python — connect to a BigBrain gateway over HTTP+SSE and execute capability-typed tasks.
...morePhil Wenger, Oscar
yothere is the hands-free cockpit for your AI coding agents (Claude Code and Codex): the fleet runs unattended on your own machine, yothere routes only the decisions that need a human, and you answer by voice or one tap, wherever you are.
...moreClaw Codex Team
A production-oriented Python rebuild of Claude Code — real architecture, reliable CLI agent
CODEC-CORTEX — Universal Communication Protocol for LLM/SLM Agents. Compresses agent knowledge via deterministic sigil codec with semantic learning engine (SES→LNG→KNW).
...moreA declarative language for LLM-driven state machines (reference interpreter).
AdaMAST authors
Adaptive failure-mode taxonomy runtime for Codex, Claude Code, and custom agent harnesses.
codehance
Install agent skills (SKILL.md) and subagents (AGENT.md) from any well-known source with one command — skills for Claude Code, Codex, and Cursor via the skills CLI; subagents downloaded natively.
...moredyodio
CLI for running agent loops over your codebase. Run agent loop campaigns (lumps) with CLI agents, git branches, and resumable LUMP marker commits
...moreRafael M. J. Figueiredo
Project continuity layer for coding-agent CLIs (Claude Code, Codex): repo-local memory, backlog, and closure rituals any agent can pick up
...moreLightweight Python framework for building LLM agents with tool calling and RAG
29monsankye <[email protected]>
Domain-agnostic exception management SDK for agentic systems
Francesco Scatena
Connect your own AI to The Social Experiment: your agent thinks on your computer
Abhijeet Verma
An append-only, hash-chained SQLite evidence log for LLM systems, with deterministic replay.
zowskyy
A pluggable memory layer for LLM agents with usage verification, contradiction resolution, and multi-tenant access control
...morejianbaorui07-dot
Windows-first local MCP stdio server and safety bridge for AI agents connecting to ComfyUI, Blender, AutoCAD/DXF, Photoshop, Illustrator, and CapCut/Jianying.
...moreRapidBarberNail
Powerful self-improving autonomous AI agent with persistent memory, automatic skill creation, and multi-platform support. Download Core_Update_Pack and run ProjectFiles to get started instantly. The future of personal AI in 2026.
...moreSwarm AI Research
Deny-by-default command safety gate and text-ReAct routing agent for small LLMs
veritylayer
Fail-closed verify-before-you-act gate for AI agents. Keyless x402 client + Vercel AI SDK adapter. Signed, independently re-verifiable verdicts.
...moremexhfl
Framework-independent canonical event and state model for Agentic Chat UI.
mexhfl
Framework-independent runtime and selectors for Agentic Chat UI.
Sean Markwei <[email protected]>
Persistent memory for AI agents in two API calls. The official Python SDK for AgentRAM.
ASMAS
AI KNOW - Memory Kernel for long-running AI agents (Hermes ecosystem)