Autonomous AI agents that perform tasks independently
cluxion <[email protected]>
Universal agent plugin for Cluxion preprocessing, honesty contracts, clarification, Rust work queue, and resource-aware harness handoff.
...moreSandeep Alluru <[email protected]>
Embeddable CRDT scene graph for embodied AI agents
aver contributors
Version control for AI agent configurations across Hermes, Claude Code, OpenCode, Zen, and Phi
erdemayaz
TypeScript OOP-based book compiling and formatting package with Puppeteer PDF generation and AI agent metadata support.
ReplayAI <[email protected]>
ReplayAI Python SDK — record, replay, and debug AI agent executions. Instrument agents with a single decorator, scrub timelines, diff runs, export regression tests.
...moreAction State Group
Reference emit + verify library for the Agent Action Capsule SCITT profile (draft-mih-scitt-agent-action-capsule). Includes the rungs 1+2+6 CORE: emit, record, anchor client, self-attest.
...moreQodeXcli
QodeX — a local-first LLM agent & AI coding CLI agent for your terminal. Runs local models (Qwen3-Coder via Ollama/LM Studio) with deterministic guardrails, 100+ tools, a real browser, smart vision & shareable live artifacts. Open source, Apache-2.0.
...morebejranonda
Autonomous self-learning agent plugin for Claude Code — 36 specialized subagents in a 4-tier architecture (analysis, planning, execution, validation), 27 skills, 41 slash commands across 10 categories. Pattern learning, real-time dashboard, full-stack validation, OWASP security. 100% local processing, privacy-first, cross-platform.
...moreLetterblack0306
The execution-control layer between AI agent decisions and real-world actions.
varib1
H2HMem evaluates multimodal LLM memory in realistic human-to-human interactions, spanning both dyadic and multi-party conversations with diverse multimodal memory challenges.
...morecodexgamerz
Interactively scaffold an AI agent skill or plugin (Claude Code plugin, OpenAI Custom GPT Action, OpenClaw, or Google ADK/Gemini) from a single spec.
...moreseandonahoe
Self-host Wayland - your always-on AI agent - on any Linux box or VPS. Headless web server, reachable from your phone.
xaviersharwin
Command-line tool for interacting with the GitAgent platform on Somnia
GitHub Actions
Core agent runtime for Rowan. Provides a configurable phase-based execution loop, tool calling, session persistence, event streaming, skills, and an extension system for plugins.
...moreHavek
agent-gyrk — CLI agentic rodando o modelo GYRK
atomic-agents-stack contributors
Spec + reference implementation for vault-native, multi-runtime AI agents
Entigram Authors
Schema-first semantic governance layer for enterprise agents
KazKozDev
A self-improving LLM agent on LangGraph that learns from experience, writes & tests its own tools, and gets measurably better over time — runs 100% locally on Ollama.
...morexoai
Iris tool boundary — ToolContract + contractDigest, the uniform ToolInvoker, real transports (in-process/subprocess/MCP-stdio/gRPC-over-http2+JSON), and the real tool_call performer. Host-side, zero external deps.
...morethe-cloud-clockwork
Configuration-driven, provider-agnostic runtime for declaring AI agents in YAML and deploying them on AWS — built on the Strands Agents SDK and Amazon Bedrock AgentCore.
...moreOne screen for every terminal coding session you have running, across Claude Code, Codex, Grok, and Gemini
Samuel Behjou
ModelRouter: fast deterministic model routing and OpenAI-compatible proxying for custom AI agents
Dockfix Labs
Autonomous security scanner for AI agents — detects prompt injection, tool abuse, data exfiltration, and OWASP ASI Top 10 vulnerabilities.
...morezernie
Lint & test the harness your AI agent runs on — verify the references in your CLAUDE.md / AGENTS.md and test that your hooks and skills actually work.
...more