Autonomous AI agents that perform tasks independently
airmang
MCP server for AI agents to read, edit, inspect, and validate local HWPX documents.
Kevoun
Agentic Research Discipline (ARD) — grounded, verifiable AI research with a .research/ substrate tier. ARD is the plugin's internal, empirically-warranted discipline (ard-core/).
...moreToken Bill contributors
Why is your agent bill so high? Profile LLM agent traces: token waterfalls, re-sent-prefix waste, prompt-cache simulation, and cache-breaker detection with concrete fixes. Pure stdlib; the demo needs no API keys.
...moreTurn successful AI agent sessions into reusable agent skills. Distill Claude Code transcripts into SKILL.md playbooks with evals-ready drafts.
...moreclipynpm
Command-line interface for Clipy — list, search, and read your screen recordings' transcripts, AI summaries, and key moments from the terminal.
...moreGitHub Actions
Portable AI-agent skills for the deliverables knowledge workers ship — diagrams, ADRs, PRDs, runbooks, decks, reviews — installable into Claude Code, Cursor, Kiro, and any IDE that takes custom instructions. One command per skill or per role-based pack.
...moretejasr
Turn websites, browser sessions, desktop apps, and local tools into deterministic CLI surfaces for humans and AI agents.
dnorio-user
Lightweight SDK to track AI agent tool calls, costs, and latency.
Dhananjay Raghu
Stateful LangGraph workflow that reviews Git diffs with a reviewer-verifier loop and deterministic checks.
eugenelim <[email protected]>
npm for your coding agent. Install packs of skills, subagents, and hooks into any repo, for every major agent.
Dan Lynch <[email protected]>
Provider-agnostic LLM adapter with streaming and multi-turn support
Dan Lynch <[email protected]>
Pi adapter for agentic-kit — the Constructive typed db tools (provision, blueprint, codegen, records, policies, templates) and confirm gate as a pi coding-agent extension
...moreDan Lynch <[email protected]>
agent — the pi coding agent with the Constructive harness baked in, purely a shell
DW-dev-UE
LLMs call your tools by writing sandboxed Python instead of JSON tool calls — 70% fewer tokens, 66% fewer round trips (measured)
...moreOpen-source Python port of Claude Code - an AI-powered CLI coding assistant
CrewAI integration for qarai-agent-guard that provides runtime security for AI agents through threat detection, policy enforcement, and content protection.
...moreMilo Nguyen
Local LLM adapter via Ollama HTTP API (default Qwen 2.5 7B)
Milo Nguyen
BLAKE3 content-addressed + zstd-delta diff storage for Orqenix KBs
Milo Nguyen
SQLite + sqlite-vec adapter for Orqenix KBs
AbuZar-Ansarii
Turn Android Termux into an autonomous AI agent and security orchestrator. Powered by a local ReAct framework with 50 system tools and MCP support, a background task │ scheduler, on-device ADB controls, and a unified Web UI & Telegram Bot.
...moreHelsinki1
coding agent harness optimized for swe-bench-style bug fixes, achieved first-run resolve rate of 52.4% on SWE Bench Lite
pamod-madubashana
Cotrex is an open-source AI execution engine that enables LLMs to securely use tools, execute tasks, and automate real-world workflows through a unified runtime.
...morelzw12w
An auditable, low-cost, DOM-only browser agent you can read and debug. Glass box, not black box: full audit trace, runs well on cheap models, no screenshots needed.
...morelittlejoely
A real local terminal in Edge/Chrome that gives Codex, Claude Code, Kimi Code, and any MCP CLI 28 browser-control tools.