Custom agents

Resilient agentic document parser & schema drift workflow automaton (Gumloop style)

No-code voice AI flow designer with industry templates & white-label reseller packaging for agencies (Synthflow style)

Institutional DCF/LBO financial model and 10-K audit builder (Rogo style)

Multi-source competitive market intelligence synthesizer (Market Research Tools)

Photorealistic aesthetic diffusion prompt and lighting synthesizer (Midjourney style)

Stateful OS-tier memory virtualization agent with auto-paging (Letta / MemGPT style)

Conversational language tutor and pronunciation fluency coach (Speak style)

Full-track generative music and vocal multi-instrument synthesizer (Suno style)

Supermarket chain omnichannel DX picker OS and wave routing (10X style)

Legal contract clause risk redlining and MSA analyzer (Harvey style)

Real-time acoustic voice interruption and turn-taking manager with sub-150ms speech cutoff (Vapi style)

Meeting bot unified API joining calls, capturing real-time transcripts and pushing signals to CRMs (Meetstream style)

Tagless personal memory stream & timeline extractor (monolog style)

Vertical beauty e-commerce omnichannel recommendation engine (Konvy style)

Livestream e-commerce multi-room monitoring & GMV sales optimizer (LiveLab style)

UGC licensing rights ledger & creator media clearance (Bazaarvoice / Tagger)

Conversational podcast dialogue audio synthesizer & multi-speaker banter (NotebookLM)

Visual DAG agent workflow tool chainer & state checkpointer (Dify / Flowise style)

Find what is wrong with the AI agent configuration your repository already has.

A self-hosted MCP Gateway for enterprise environments. Secure AI agent connections to MCP servers with tool governance, multi-tenant isolation, and full observability. Built with Rust and Vue.

The framework client-facing teams use to build internal & client apps with AI. Two agents — a Product Owner that advises what to build, and an AI Developer that ships it. Built by FuseBase.

Learn Machine learning by doing exercises and intuitive animations

Secure agent automation with full audit trail, human approval gates and compliance-grade orchestration (Tines 3B style)

Field guide and local-first tools for token and context optimization in LLM agents.

Local-first persistent memory infrastructure for DeepSeek Harness: hot bootstrap, Chinese-BM25 cold recall, lease-lock transactional writes, read-only governance

Open-source Object Context for software teams and AI agents. Maps real code into business objects, logic and dependencies, shows change impact, serves relevant context over MCP, and verifies outcomes. Local-first.

Multiplayer Agent Management Platform — agents as infrastructure. Host teams of agents that work together and run your business.

Ask in plain language, get ranked real data sources — then an agent builds, validates and runs the scraper for you. The validator cannot rubber-stamp its own work.

An AI agent for Ableton Live

A lightweight, memory-budgeted GGUF inference runtime and developer playground for running small language models on constrained devices.

Local-first desktop AI agent platform built with TypeScript, Electron, React, and SQLite.

0xNuller — unified Control, Agent, Voice, Chat, Playground and Market for Web and Android

CUMCM 国赛 AI skill 包：读题到交卷。C 题走数据契约，A 题走机理/PDE（单位、守恒、网格收敛）。支持 Claude/Codex/Grok/opencode。

90,896 Hermes Agent skills — 79k+ shipped as COMPLETE offline folders (SKILL.md + scripts, references & assets). Instant offline search across ClawHub, skills.sh, LobeHub, gstack & more.

Self-hosted voice AI agent infrastructure builder for inbound/outbound calling with STT, TTS, LLM routing (Dograh style)

Realtime duplex voice agent turn-taking & barge-in interruption detector (LiveKit)

Realtime multi-party audio transcript diarization & speaker assigner (Deepgram)

UGC creator brief programmatic auction & video matchmaking (Cohley)

🏪 Telegram-бот магазина на бесплатных ключах Google Gemini: ротация ключей при 429, каскад моделей, три личности продавца, каталог, корзина, QR-оплата

Windows用デスクトップ向けAPI/ローカルLLMクライアント。ペルソナが話しかけてくれたり、天気取得/ウェブ検索/URL読込みもできるよ。

Mutation testing for your LLM evals — degrade the system under test and check whether your evals would actually catch a regression.

A messenger interface for the Antigravity AI agent. Features interactive CLI tool approvals and voice control

Touhou-inspired Agent Skills: distinct, testable, composable problem-solving workflows.

GenPark skill: Utilize GenSpark Workspace 4.0 for desktop automation, MS Office integration, and AI meeting notes.

Você não começa do zero — chega com impulso. Guarda as peças de site que você já fez e as encontra de volta antes de gerar qualquer coisa outra vez. Agent Skills para Claude Code, Codex, Gemini CLI e Cursor.

北极星方法论：保持目标、验证结果、从失败中恢复。仅限个人研究；禁止商用、再分发、AI 训练与蒸馏。 | The methodology behind Polaris: keeping AI-driven work on track, checking results, and recovering from failure. For personal research only; no commercial use, redistribution, AI training, or distillation.

Observability infrastructure for self-improving agents: every run written into the repository as plain files the agent can read

One delegation policy for Claude Code, Codex CLI and T3 Code: role-based headless workers, worktree locks, cross-vendor review, safety gate hook.

Cryptographic receipts that prove an AI output was not altered. Offline verification in 21 lines, no server or account. Ed25519 + SHA-256, 128-byte Rust core, optional ML-DSA-65 post-quantum signatures. Python and Rust.

Lunar Vault is a self-contained memory infrastructure for Codex. Features zero-dependency ONNX embeddings, advanced reranking, and secure one-click installation without leaking personal data

A desktop app that turns Claude Code into a visual Kanban build loop. Describe a feature, review the plan, watch it get built task by task.

Deterministic execution & evolution layer between AI intent and production software — turning structured intent into reviewable, reproducible code. 🔥

Native macOS Markdown viewer and rendered-diff reviewer for documentation-heavy GitHub PRs (design docs, ADRs, skills, runbooks)

Connect AI agents to live QGIS Desktop through a secure local MCP bridge with 100+ specialist tools and resumable visual workflows.

Native macOS deck for orchestrating AI coding agents, each in its own terminal and git worktree

GenPark skill: Automate enterprise project management and query workspace knowledge bases using ClickUp's hierarchy APIs.

OpenClaw skill: genpark omnivideo

【已停止维护】原名 BIT · 本地优先的桌面端 AI Agent 工具中枢（工具注册 / MCP / 技能 / 远程 API）— 已更名「触手怪 Tentacle」，新仓库见 yxpil/BrainTentacle

🐾 Autonomous Multi-Agent Crypto Intelligence Swarm. 15 AI Scouts monitoring Solana, Robinhood Chain, Base, ETH, Ink & Hyperliquid 24/7.

Agentic dev workspace & live telemetry feedback loop (Xirp style)

A coding agent that brings the full development loop to your phone — code, run, test, and iterate from anywhere.

GenPark AI Agent Skill - DPLL (Davis-Putnam-Logemann-Loveland) Boolean satisfiability solver with unit clause propagation and pure literal elimination for agent policy verification.

GenPark AI Agent Skill - First-Order Logic (FOL) resolution theorem prover applying Most General Unification (MGU) and refutation proof trees.

GenPark AI Agent Skill - First-Order Logic (FOL) resolution theorem prover applying Most General Unification (MGU) and refutation proof trees.

GenPark AI Agent Skill - DPLL (Davis-Putnam-Logemann-Loveland) Boolean satisfiability solver with unit clause propagation and pure literal elimination for agent policy verification.

A terminal coding agent where the model writes one program instead of calling tools one at a time.

RLE: harness × model benchmark on a live RimWorld colony. Swappable agent harnesses (Felix multi-agent, coding agents over MCP, or your own plugin) are scored identically against an unmanaged baseline. FLE for multi-agent coordination under uncertainty.

A local first agentic coding chat interface aimed to deliver great looks while promising feature rich experience.

Dark Linear/AI-OS style technical diagram skill — cyan/purple/lilac duotone SVG diagrams

Free, open-source, local-first AI agent desktop app — a Claude Code / Cursor / Copilot alternative. Reads & writes files, edits code, runs commands. No setup, no API key needed. Windows, macOS, Linux.

The Best and most functional MacBook Dynamic Island (See the Unseen)

AI 智能学习助手系统：基于 Spring Boot 3.3 + Java 17 + Vue 3 + Qdrant + Redis，实现AI学习助手、RAG检索评测、资料管理、在线练习和学习分析系统，适合作为学习和简历项目，学习门槛低。

A benchmark for LLM-driven bug discovery: 77 challenges across 43 open-source projects (C/C++/Java).

`grill-me` is an agent skill that tests whether you understand the code you maintain—not merely whether your coding agent can change it.

Cookbook for custom AI agents on SAP BTP across all regions and regulated deployments — including China, NS2/sovereign, KSA, ahead of BAIP GA.

Learning assistant extension for DeepSeek Harness (dsh): brings DeepTutor tutoring to your agent — deep explanations, self-test questions, learning paths, personal knowledge-base search (RAG), and note archiving. | 面向 DeepSeek Harness 的学习辅助扩展:为 agent 接入 DeepTutor 辅导能力 —— 深度讲解、自测题、学习路径规划、个人知识库检索(RAG)与笔记归档。

Long-term memory MCP server for AI coding agents. SQLite + FTS5 + vector search, CodeGraph, error learning, compaction survival. Beats Mem0 on benchmarks. No cloud, no API key.

ai harness for discord maybe

Ai coding harness, written in rust with a large number of Model Providers and complex orchistration of LLM agents.

Local-first AI companion for Windows with a Live2D avatar: local speech transcription, local LLM replies, local TTS, and screen awareness.

Proactive AI executive assistant for meeting scheduling & agenda synthesis (Hey Noah style)

Visual workflow canvas orchestrator for modular LLM pipelines (Dify style)

CrestApps.Core is the AI application framework for .NET. It gives you the orchestration, management, chat, document, RAG, MCP, A2A, agent, reporting, and extensibility building blocks needed to add production-ready AI to an existing application without stitching together a pile of disconnected SDK samples.

Lightweight graph engine for AI graph context, memory, and agent harness with Rust Core.

Ephemeral cloud developer sandbox and live tunnel spawner (Replit style)

Self-deployed AI-native project management platform—requirements, acceptance, and progress stay in your instance, running synchronously across sessions, users, and Agents.

A persistent, browser-accessible Linux computer for a single Buzz agent — its own desktop, terminal, filesystem, and long-lived state, joining any Buzz workspace over its relay

Agent Skills and plugins for using Relewise with AI agents, including ChatGPT/Codex, Claude, GitHub Copilot and Gemini.

AI Agent Skill for building verified, citation-backed courses in Google NotebookLM

Autonomous fullstack app scaffolder and live provisioner (Replit Agent style)

Local, searchable project memory for AI coding agents. Markdown source of truth, MCP interface, safe structured updates — no cloud.

DBOS durable execution for the Vercel AI SDK

gwae: niri's scrolling tiling for your CLI agents, in any terminal (daemon-free, MIT)

Autonomous Agent Earley Context-Free Grammar Chart Parser with Arbitrary Ambiguity & Recursion

Autonomous Agent CYK (Cocke-Younger-Kasami) Probabilistic Context-Free Grammar (PCFG) Parser

Autonomous Agent Earley Context-Free Grammar Chart Parser with Arbitrary Ambiguity & Recursion

An end-to-end framework for Agentic Reinforcement Learning.

Agent Skills-compatible skill: batch-rename, annotate & tag untagged design assets in Eagle via eagle-mcp. Works with Claude Code, Codex CLI, Gemini CLI, GitHub Copilot, Cursor & WorkBuddy.

Autonomous Agent Multi-Armed Bandit UCB1 & Thompson Sampling Exploration-Exploitation Optimizer