Havuz

SSH MCP server: execute commands, transfer files, and forward ports on remote servers via MCP.

The DeepSeek and OpenRouter Harness built on Elixir

Structural code intelligence for DeepSeek Harness (dsh) — gives the agent codegraph and codegraph_index tools to find where a symbol is decl

Isometric games made easy — an agentic game kit. 12 agent skills over 9 zero-dependency TypeScript packages. Type one sentence, get a playab

Save conversations, search by idea, read the surrounding context. Memory for AI agents.

A static performance model for LLM inference: given (model, GPU, interconnect, workload), instantly answer VRAM feasibility, latency(TTFT, T

See and manage what your coding assistants load — skills, commands, subagents, plugins and MCP servers, with real usage.

Mail for AI agents ( and humans). MCP server giving Claude (or any agent) safe, permission-controlled access to email (Microsoft Graph + IMA

An automated, multi-turn LLM red-teaming pipeline that pits an Attacker model against a Target model to evaluate safety boundaries, featurin

Fast, idiomatic Go MCP server for web search, image search, and page scraping to Markdown. Runs locally, no API keys, free.

Minimal harness-agnostic recursive language model layer — one binary, Python + llm()

Self-hosting ChatGPT/Codex Plugin autopilot — copy-in, repo-owned. Converts agentic repos into validated, deterministically packaged Plugins

Adversarial LLM Reversal for hermes-agent

FAAAH (Filesystem As An AI Handler) - Reuse your AI Agent subscription via text files.

A pi extension with a single tool: execute, running TypeScript in a persistent Bun evaluator. Files, shell, and subagents are expressed as c

Turn any tutorial video into a verified, installable AI-agent skill. Reads the screen, not the transcript. Runs locally. MIT.

Any agent that can run curl gets a real browser. Snapshot a page as refs, click one, read the JSON behind it — no SDK, no MCP, no API key.

不死鸟 Phoenix — Hermes Agent 插件：路由分档/风险防线/自愈/存档点提醒/审批策略自适应，官方钩子接入，不改 Hermes 核心代码

Bounded repository context and verified patches for Codex and Claude Code. Explicit edit grants, source fingerprints, isolated worktrees, ac

A graph-native simulation engine for building composable engineering simulations and digital twins.

Desktop app for managing AI Agent skill files and prompt templates across local folders, GitHub repos, and online links. 跨平台的 AI 技能与 Prompt

Open-source, license-free MCP server for RTL waveform debug: reads FST waveforms (VCD/FSDB auto-convert) plus a SystemVerilog netlist, with

Checks every AI agent action against your company's real rules before it runs. Git-native, PR-reviewed.

Repository-scoped memory for coding agent's decisions, pitfalls, and handoffs stored in one inspectable SQLite file, so agents continue inst

"Review Ducktective" is an automated code review platform based on an LLM: it takes a diff as input and outputs structured findings with sev

U-Pool, Claude Code, Codex ve diğer AI-coding araçlarının provider ayarlarını, API key'lerini ve modellerini masaüstü arayüzünden yönetip değiştiren bir uygulamadır.

Neden yükseliyor · Ölçülebilir yükselişin nedenini doğrulayacak son 28 gün commit ve yazar verisi yok; 64 günlük yaşına karşılık 17 yıldız da belirgin benimseme kanıtı sunmuyor. Çoklu AI-coding aracı ve provider yönetimi tek arayüzde toplama fikri ilgi çekici olabilir, ancak trend iddiası için veri yetersiz.

Production agent skills for Claude Code, Cursor, and any SKILL.md harness — Codex fleets, video pipeline, monorepo review bundles, multi-cha

Tools Are Not Islands: Set-Level Tool Retrieval for LLM Agents via Query-Conditioned Hyperedge Prediction

A live, local dashboard to browse, search, resume & manage every Claude Code session on your machine — full conversation transcripts, an art

Tools for AI agents to test, fix and optimise your codebase

An educational macOS app: build and chat with a tiny language model, trained on your Mac

Agent Skills and lightweight tools for clearer, more natural Vietnamese writing, translation cleanup, grammar checks, and style consistency.

CLI and a Chrome Extension designed for you to review AI generated code locally and on GitHub PRs

Kimi Code-style agent orchestration harness for the Pi coding agent — Swarm, Goal, Plan, Permission, Task, Hooks, Skills, TUI

Fast, deterministic verifier and gate for AI agents: exact math, claim and citation checks, shell/write policy, hash-chained step ledger and

See which of your AI agent skills actually get used — one local library for Claude Code / Codex / OpenCode skills, with real trigger counts

Send messages from AI agents, CLI, and MCP tools - powered by one shared TypeScript core.

OKF (Open Knowledge Format): Durable, structured memory for AI agents. Author, validate, consume, and maintain portable knowledge bundles th

Control Ableton Live from an AI assistant. 156 tools for building, editing MIDI, mixing, and mastering in a running Live set. Typed, tested

Translate academic papers & monographs (PDF) into a single self-contained bilingual HTML — Chinese/original/side-by-side. Vendor-neutral, wo

MCP server: gives your AI agent the real sources, public API and KDoc of any Maven/Gradle-published Kotlin or Java library

This is a fork of the https://dockbox.dev project I made

waggle, agent'lar arasında artifact'ları kopyalamak yerine kısa referans token'larıyla aktararak her tüketicinin ihtiyacına göre çözümlemesini sağlayan bir handoff katmanıdır.

Neden yükseliyor · Agent harness'leri ve multi-agent orchestration'a yönelik ilgiyle örtüşen, handoff'taki context tekrarı ve izlenebilirlik sorunlarına odaklanıyor. 82 günde 648 yıldız erken ilgiye işaret ediyor; ancak son 28 günde commit ve farklı yazar sayısı sıfır olduğundan güncel geliştirme ivmesi olduğuna dair kanıt yok.

Mnemovela - Agent Cognition Runtime (typed memory, Git-like branches, hybrid retrieval, governed forgetting; embedded-first Python & Go). Op

BuildArena: Physics-grounded Besiege Building for LLMs

Enchant Version of 9Router. 304+ Providers (API-key, OAuth, free-tier, and 39 web-cookie providers), 6 combo strategies (fallback, round-rob

CodeScope does not understand code. It verifies it. A high-performance code graph engine with MCP protocol for AI agents (Claude/Cursor) to

Full job-hunt Claude skill bundle — Job Description decoder + Resume builder (11 templates) + Behavioral Interview / story bank. Three self-

Excalidraw MCP server with real vendor-icon search & insertion (AWS/Azure/GCP/OCI/Kubernetes) for AI-built architecture diagrams — live canv

Give your AI agent the parts of the internet web search doesn't reach. An add-on for Claude Code, Cursor, and Codex: podcasts and videos, Bi