Autonomous AI agents that perform tasks independently
RNT56
Self-hosted, privacy-first AI collaborator with durable memory, real tools, channel-native access, routines, and auditable autonomy.
...morelihroff
placeholder package for the agenticode project
Data models and validation for the AI Agent Builder ecosystem
Core library for the AI Agent Builder ecosystem
GitHub Actions
Deterministic Run402 release manifest semantics: schema versions, canonicalization, materialization, diffing, and compatibility fixtures.
...moreGitHub Actions
Codex skill for managing Codecov coverage, API inspection, uploads, flags, reports, and repository configuration.
fresp
AI agent orchestration framework for OpenCode — PRD to engineering docs pipeline
dadion123
Doctor-first CLI for keeping AI coding agent context files clean, minimal, consistent, and safe.
GitHub Actions
Spec-Driven Agent Framework - Desenvolvimento orientado por especificações para agentes LLM
lintaoamons
UnDercontrol CLI - task and expense management from the terminal
Yuggohel2
A highly efficient, collaborative agentic coding framework using Model Context Protocol (MCP) to divide work between planning, code graph analysis, and execution.
...moreOnourImpram
Human-supervised career decision safety with claim graphs, high-stakes gates, and append-only audit.
owainlewis
An agent-first OCaml implementation of an R7RS-small Scheme interpreter.
"B.T. Franklin" <[email protected]>
Typed declarative contracts for AI agent systems.
cyberfascinate
Creduent is the open application-layer protocol for cryptographic identity and trust verification of autonomous AI agents using Ed25519 and DNS.
...moreRawson Consulting B.V.
Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.
...moreGrammy Jiang
A Socratic questioning skill for coding agents (Claude Code, Codex, Copilot), with a one-command installer and an idea-brief validator.
...moreshichuanqiong
Hermes Agent plugin for a2a-dm — real-time agent-to-agent DMs + groups over the A2A 1.0 protocol. Ships SSEDaemon-backed inbox listener, 12 typed tools, slash commands, and pre_llm_call wake injection.
...moreVeera Ravindra Divi
A reference implementation and methodology for measuring the reliability of LLM agents (the Assevra Reliability Scorecard).
...moreKochC
Local AI gateway for OpenCode with tool/function calling — use any model via OpenAI, Anthropic, or Gemini API
nathansutton
Local MLX coding agent for Apple Silicon — Claude-Code-style tools + TUI on a laptop-sized model 🗿
thomasnrs
Production-ready autonomous AI agent for software engineering, featuring planning, coding, memory, and continuous self-improvement. OPEN SOURCE.
...more910636071
A security-first agent platform — Models Propose, Records Decide. 17 deterministic constraints gate every LLM proposal before it becomes state.
...moredoodle contributors
A linter for Claude SKILL.md files.