Custom agents

Self-hosted workbench host for AI coding agents. Each project gets a themed dashboard where the agent drops approval forms, runbooks, files, and review docs — out-of-band from chat, persistent, auditable. FastAPI + Svelte 5, single static binary or Docker, single-user.

Telegram Bot Customer Service Platform - Multi-bot pool, bidirectional messaging, FAQ engine (8 modes + AI), real-time web chat, user management. Python/FastAPI + React/TypeScript + PostgreSQL + Redis. Docker deployable.

An opinionated agentic development layer for OpenCode — spec-first when it matters, review-driven execution, portable model roles, safer tools, and long-run safety.

Open-source AI assistent with voice interaction, automation and enginering tools

Let Codex and Claude find, download, and read full research papers. A local MCP server with six academic sources, Unpaywall, and optional Zotero sync.

Put an AI agent on rails: mount a Burr state machine as an MCP server so the agent can only take the next allowed step, with every step recorded and replayable.

Autonomous YouTube AI agent: LLM script, TTS voice, stock clips, FFmpeg editing, AI thumbnail, auto-upload — 100% free, Telegram-controlled.

SentinelX agent: outbound-only agent that exposes your Linux, macOS, and Windows servers as MCP tools to Claude.ai and ChatGPT

build eval for your agent in 10 mins

Windows-first local MCP stdio server and safety bridge for AI agents connecting to ComfyUI, Blender, AutoCAD/DXF, Photoshop, Illustrator, and CapCut/Jianying.

Architecture rules your AI coding agent can't break — generates AGENTS.md, per-folder CLAUDE.md, and Claude Code hooks from your codebase.

Deploy an army of agents or architect an immersive game world in minutes. The barrier between your imagination and code is now gone

Blockchain skills you can use with your coding agent, such as Claude Code, OpenCode, Codex, Cursor and more.

Agent-safe GPT Image 2 prompt/reference toolkit with identity, style, edit, dry-run and receipts

AI-Powered Code Toolkit for Game Engines

Two Claude Code skills for adversarial code review (single-model PAR and multi-model MMAR with cross-critique to catch hallucinations), plus a fixture-based eval suite.

ARES is a self-healing multi-agent runtime that combines event sourcing, memory distillation, chaos engineering, and evolutionary workflow optimization.

Rust implementation of the Agent Skills open standard with validation tools

Extract, chunk, and embed documents from 88+ formats directly into SurrealDB.

Semantic retrieval for AI agents: high-recall memory and code search that cuts coding-agent token usage by nearly 50%

Proof-of-done for AI coding agents. Local evidence receipts for Codex, Claude Code, Cursor, and GitHub Actions.

為 Agentic AI 新手友好的輕量項目記憶與治理套件：把狀態、決策、下一步、文件地圖、新手引導與工具邊界寫成標準檔案，讓不同 AI 工具可在同一項目資料夾內跨 Session 對話延續工作。 A beginner-friendly project memory and governance kit for Agentic AI, helping AI tools continue work across chat sessions with standard project files.

Self-hosted, open-source AI resume builder for software developers.

🚀 Financial Anomaly Detection with DeepSeek and Isolation Forest – A powerful, locally-run tool for detecting financial anomalies using Isolation Forest and DeepSeek LLM. Features AI-powered insights, interactive time-series visualization, and automated PDF audit reports. 🔍📊

A self-hosted household AI chat app built on OpenClaw — multiple conversations, multi-user family life, and long-term memory on your hardware.

One AI engineering team for Claude Code. Install once — every project gets a full-stack specialist team that auto-specializes to its stack.

Full-stack GraphRAG application with Django backend and React frontend. Build knowledge graphs, detect communities, and chat with documents using hybrid retrieval and LLM-powered reasoning.

154 Web3 MCP tools for Claude Code, custody-free. Plus an agent wallet prompt injection can't drain: per-tx, daily, and on-chain (ERC-4337) spending caps the model can't bypass. EVM + Solana + Tron DEX/DeFi, perps, prediction markets, contract deploy + audit.

AI-powered novel writing system with dual-system support (male/female-oriented), framework agents, and multi-dimensional quality evaluation.

The Analytics Database for Agentic AI — Free for Personal Use

Evidence-grounded skills and software-tool records for scientific AI agents, distilled from method papers by the AgenticScienceBuilder pipeline. Metabolomics: 5,859 skills, 909 tools, 21 workflows.

Agent tools from many descriptions in a single integration. Authorize operations, not just tool calls, and approve them when a human is required. The agent gets its own identity and never holds your credentials.

Bring an idea. Leave with a working MVP. Lullabeast is a gated multi-agent pipeline that gets results from cheap open models. Run it with cloud, local, or mix and match. You choose!

Open re-implementation of Claude Code's built-in Dynamic Workflow: a script-driven runner for agent-authored JavaScript workflows — agent(), parallel(), pipeline(), token budgets, git-worktree isolation, deterministic resume — plus pandacode, a pluggable executor for codex, claude, and domestic LLMs. Auto offline HTML execution-graph reports.

A fully locally deployable, NotebookLM-like application designed for long-form unstructured documents

A self-correcting system of nested engineering loops: plan & execute repo work; safely implement audit findings; design greenfield & improve brownfield; learn from failures; re-verify until closure.

SkillBill packages your engineering judgment into governed skills, then uses a durable Kotlin runtime to ensure agents actually execute that process consistently, resumably, and with bounded context.

The open-source AI infrastructure stack for Swiss enterprises.

BS AI FAST NUCES Coursework material from 2022 - 2026. Access Course Outlines, Books, and Slides with ease.

Fine-tune a local LLM on your own chat history to mimic how you write — an AI doppelganger / digital-twin toolkit built on LLaMA-Factory (LoRA SFT).

Pure-Rust DWG -> multipage PNG renderer + lossless position-referenced text layer & metadata indexer for RAG/VLM ingestion of CAD drawings

Python algorithmic trading suite: signal generators, backtests, and a multithreaded paper-trading runner for NIFTY/BANKNIFTY/FINNIFTY via the Dhan API. Also contains a Claude-based AI agent for SL hunting-based strategies and a Codex-based AI agent for CPR-based strategies

OR-Space: a full-lifecycle workspace benchmark for industrial optimization agents

Local-first AI workspace for law firms: case files stay on your machine, local or chosen cloud model, hash-chained audit trail with its own verifier. 9 editions. AGPL-3.0.

Runtime-aware Skill routing for Codex: choose the smallest verifiable Skill set across single tasks, phased work, and managed goals.

Self-hosted orchestrator for Claude Code agents: drive ideas through a role-gated SDLC (plan → build → test → release), with per-agent sandboxing, live run streaming, and markdown-on-disk as the source of truth. Single Go binary.

Detent is board-driven agentic work orchestration, shipped as a single Go binary — it watches a GitHub Projects board and runs each ready issue through an isolated Git worktree, a coding agent, your validation gate, and a serialized merge train, live on web and terminal dashboards.

Closed-loop agentic development workflows for Claude Code, Codex, and Gemini CLI.

187 plug-and-play AI agent personas на русском языке — Russian translation of agency-agents + 3 Russian-market originals (Wildberries/VK/Yandex SEO)

Models Take Notes at Prefill: KV Cache Can Be Editable and Composable (arXiv:2606.17107) — paper, code, results, and interactive companion.

Composition root for production agent services — fork, customize, ship. Built on the foundry-agent-* packages.

Self-hosted, single-file Indian portfolio tracker with AI insights, Gmail expense tracking

One open A2A 1.0 mesh for Claude Code, Codex, Cursor, Cline, Continue and Gemini.

Agentic Content Creator to increase views & followers across different social media: Youtube, Tiktok, Instagram

⚡ A floating, agentic DeepSeek AI assistant that overlays every app on Android — clipboard quick-actions + a chat that can run shell commands on your device. Pure Termux + Termux:GUI bash.

Gatemole compiles human-owned intent into obligations, links evidence artifacts to those obligations, and produces deterministic release decisions for agent-written changes.

AetherLearn is an agentic AI-powered educational video generation platform that orchestrates multiple AI agents using LangGraph to convert text, PDFs, and images into high-quality narrated animated lessons with OCR, Gemini, Manim, TTS, and FastAPI.

Kagenti Agent Development Kit

CLI & async Python library for free AI chat, image & video generation.

Zeno —— 本地优先的单二进制 TUI AI 编程工具。多智能体协作 + 安全沙箱 + 插件可扩展。基于 bun + TypeScript，类似 Claude Code / OpenCode / Codex CLI。

An institutional-intelligence operating system: a council of 14 agents that remembers every deliberation, grades its own predictions against reality, and revises what it believes. Runs on your machine — Ollama, llama.cpp, or any cloud API.

[ACL 2024 🔥] Video-ChatGPT is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrained visual encoder adapted for spatiotemporal video representation. We also introduce a rigorous 'Quantitative Evaluation Benchmarking' for video-based conversational models.

AI coding agent that shows its work — every step visible, every patch approved by you. Build projects brick by brick, stay in control.

Local-first, IM-native AI coworker runtime with async role agents, trace replay, evidence, and agentic evaluation.

Web dashboard for viewing AI agent session logs — supports OpenClaw, Codex, and Claude Code | 多平台 AI Agent 日志查看面板

One binary. One SQLite file. Your own AI assistant.

Your AI cofounder that rides along

Volt Deep Research is a sophisticated multi-agent orchestration system built on VoltAgent that automates complex research workflows. It combines specialized AI agents, semantic memory, intelligent tooling, and custom web scraping to conduct comprehensive research, verify facts, analyze data, and generate publication-ready reports.

A production-ready, multi-channel AI agent for AIOps, Kubernetes management, and automated remediation — built on FastAPI with support for GitHub Models and Google Gemini LLM backends.

An open-source AppSec agent that reasons like an analyst: real scanners, your org's context, and a conversation instead of 400 findings.

Typst Open-Source Server for collaborative editing

Hermes desktop achievements: full achievements page + sidebar nav + statusbar score chip, backed by the bundled hermes-achievements plugin API. Zero new backend.

Handle agentic tasks using 50+ AI providers on web

Skill letting Agents scan a repo, ask what it cannot infer, then generate a complete open source file collection i.e. README, LICENSE, contributing, security, changelog, CI, launch playbook, etc.

An Android Agentic harness supports all local and remote models.

Open-source Bittensor subnet for a global AI agent competition in sales intelligence

Local-first personal knowledge base CLI — hybrid FTS + pgvector search, a GraphRAG entity graph, and LLM enrichment over your notes, transcripts, Slack & Gmail. Runs fully local on Ollama (no cloud, no API keys); queryable by any AI agent through the built-in MCP server. Postgres-backed, publishes an Obsidian-style Quartz wiki.

Sách miễn phí tiếng Việt về vibe coding cho Tester, PM, BA — người làm IT không viết code. 20 chương, 3 phụ lục, 54 hình. Học cách chỉ đạo AI coding và đánh giá kết quả: quy trình 5 giai đoạn, prompting, PRD, đọc hiểu code, test, bảo mật. Tải PDF/EPUB ở Releases.

Curso System Design Interview Notebook LM - From Zero to Production

Fully local AI meeting assistant: speaker diarization + self-updating knowledge graph. Nothing leaves your Mac.

LJHskill（老家伙 skill）电商增长工具箱：全网首个免费开源的内容电商增长赋能 skill 合集，总共 25 个业务工具。你只需要告诉我你的业务困惑是什么，我会自动选择合适的工具帮你解决问题。

AI agent skill for Avito Business API: manage listings, messenger chats, delivery, orders, vacancies, autoload, statistics, promotion. Works with Claude Code, Cursor, Gemini CLI, Copilot and 30+ AI agents.

Autonomous pipeline that finds energy and CO₂ hotspots in any codebase and ships efficiency fixes proven by embedded statistical A/B testing, correctness gates, and integration tests reverse-engineered from the real system.

The zero-trust framework for autonomous AI agents.

Typed, pure-HTTP TypeScript SDK for your own Tesco grocery account — search, basket, nutrition, delivery slots, and orders over plain fetch. Browser only for login + payment.

Privacy-first AI novel writing IDE. Full workflow: outline→draft→review→finalize. Local RAG + multi-model routing. Trilingual UI (zh/en/ru) + multilingual prompts. GPL-3.0 open source.

Run powerful AI models entirely on your Android device. 100% offline, private, no API keys. Built with Kotlin, Jetpack Compose, Material 3, and llama.cpp. Download GGUF models from Hugging Face. On-device LLM inference for Android.

A coding agent that lives in your terminal. Local Ollama first, or hosted models through the Aether AI fleet.

📱 IRIS-MX is a premium, voice-first mobile AI assistant built for high-performance execution. Automate tasks, query web search, and analyze live visual context—all driven by fast, zero-friction voice commands. Designed as the ultimate pocket productivity tool.

The world leaderboard ranking for AI usages.

Open-source Polymarket AI trading bot — multi-agent news swarm for fair-odds edge detection, Kelly sizing & CLOB paper/live execution.

EvolveX is a research framework for principled agent self-improvement. It evolves prompts, skills, and agent code under frozen evaluators and declared mutation boundaries, recording verifiable lineage — scores, artifacts, and Git-tagged generations, so every improvement is reproducible and auditable.

Agent memory that needs no API key, no LLM, and no embedding provider. One command on Bun and it is serving MCP over stdio against a local SQLite store. Drop-in for the MCP reference memory server. Every memory keeps its source, who may read it, and the evidence that contradicts it.

Cuts the token bill of AI coding agents: compresses shell output, blocks token-hungry calls before they run, prices your session live, and rescues sessions whose prompt cache expired. Bun + Claude Code.

Agentic terminal forked from the holy Alacritty.

Profer — 基于 Claude Agent SDK 和 Pi runtime 的通用 AI Agent 桌面应用：多模型接入、协作子 Agent、定时任务自动化、平板远程接入与团队工作区。

一只会主动关心你的桌面 AI 桌宠：双角色、长期记忆、工具调用（PySide6 + DeepSeek） | Windows desktop AI pet companion: dual characters, long-term memory, function calling

aiduPOP☤爱嘟泡波浪 (aidu-customized Feishu/Lark streaming card plugin for Hermes Agent)

Fully local document intelligence for DeepSeek Harness. Parse PDF, Office files, images, and scanned documents with offline OCR. | DeepSeek Harness 全本地文档智能插件，支持 PDF、Office、图片与离线 OCR