Custom agents

Go CLI and library for safely running Splunk searches from SPL or YAML and saving results with job diagnostics.

Self-hosted AI workstation for a compatible Linux VPS: agent chat, project workspaces, apps, shared browser, remote desktop, terminal and optional mail. MIT licensed.

Your project remembers across coding agents. Compact, cited project memory for Codex, Claude Code, Cursor, and compatible tools.

DSH 拖拽文件转路径插件：Codex 式拖拽，路径自动插入输入框（Drop File to Path for DeepSeek Harness）

Full-duplex streaming voice agent pipeline (Dograh style)

DeepSeek 桌面版客户端（社区构建，非官方）：下载即用，无需 Node。Download-and-run desktop build of DeepSeek Harness — Electron shell, no npm required.

Declarative agent runtime in Go: define governable AI agents as YAML, not code — run them headless, as a service, or on triggers, with policy, limits and an audit trail built in.

Lightweight one‑click launcher for DeepSeek Harness DeepSeek‑Harness(DSH)轻量一键启动器

🪐 Growmos: A new approach to agentic AI—a living system expanding its knowledge like the universe, compounding its capabilities, and getting more work done with fewer tokens.

Solidity contract auditor: bundled JavaScript call-graph extractor (@solidity-parser/parser) plus a stdlib Python CLI that POSTs each function to a Model Alpha audit endpoint.

Evidence-backed, explainable multi-model routing for DeepSeek Harness — policy resolution, provenance, and compatibility boundaries.

World-class travel planner skill for Claude Code. 7-phase workflow grounded in current web intel, modeled on Wendy Perrin, Indagare, Black Tomato, and Riveting Trips methodologies. Source-available, non-commercial.

Agents as plain Ruby objects. Fields are state, methods are tools, and the methods you declare without a body are written by the model at runtime.

Turn corrections from AI agent logs into guidance for similar tasks. Local memory with semantic retrieval, prompt-context hooks, and response checks.

Mission control for your agent swarm — know which agent is working, which is stuck, and which is done. Works with 14 coding agents, runs entirely on your machine.

MonoLight 是一个专注于安全执行与人机协同的通用自主智能体（General Autonomous Agent）运行时。

Interactive multi-agent collaboration, meetings, group chats, and task execution for DeepSeek Harness.

Self-contained demos for the Nutrient Data Extraction API — grounded extraction with per-field citations, bounding boxes, and confidence scores.

DeepSeek Harness（dsh）动态 Cordis 插件：模型高可用回退 + 五种模式子智能体编排（fanout / pipeline / supervisor / map-reduce / router）

AI session retrospectives — skills and prompts that let your AI agents bring their feedback to your retro

DSH execution-discipline plugin suite: 11 plugins + 6 skills, zero dependencies, 426 tests. 让 DeepSeek Harness 变聪明的插件套件。

Sane policies for insane agents

A gateway + skill letting Claude Code agents collaborate across machines

SciSage: multi-agent scientific survey generation with hierarchical reflection; includes the SurveyScope benchmark.

Ethics-aware OSINT investigation planning, collection, and risk evaluation, delivered as an MCP server. Classification, risk tiers, hard stops, and defensible documentation — driven by local YAML doctrine.

AMH WT: approval-gated Cloudflare tools for your AI. Text a job to WALO on WhatsApp and a cloud agent does it, no PC or terminal needed. Or add WT as a connector in Grok, Claude or ChatGPT on your phone or PC. Inspect, publish and verify site changes; Git optional.

Open specification and reference verifiers for Seal records: ATTESTATION-v1 for AI model calls, ACTION-v1 for agent actions, and GRANT-v1 approvals (draft). Ed25519, canonical JSON, checked offline against a published key.

SNAFU. Agentic LLM flow to help you with "naming things" in source code.

Your always-on AI assistant — you state the goal, it assembles the managers and sub-agents it needs. Self-hosted multi-LLM agent runtime: Telegram/Web/CLI, skills, memory, MCP.

Evidence-grounded AI secretary for Claude Code and Codex, with frozen context, deterministic retrieval, bounded quality review, and explicit human approval gates.

Talk to Claude Code instead of typing: a voice daemon + dashboard that records you, transcribes, routes to your agent sessions, and speaks the replies back - with per-voice avatars, push-to-talk hotkeys, and a live conversation HUD

The reference app for AI-written enterprise software: a complete CRM in typed ObjectStack metadata — business logic under 100k tokens. Small enough to hand an agent in one context window.

Reference agentic application combining Angular, A2UI, generative UI, and human-in-the-loop workflows.

A modular framework for agentic Bayesian optimization

A lightweight Android AI role-playing chat client.

⛵ 职航 · 求职助手 — AI Agent 驱动的秋招求职看板：轻量级求职进度管理看板，支持校招岗位智能搜索、简历定制、面试进度追踪，一站式投递管理

把中文视频逐字稿转换为可执行 HyperFrames 分镜规格的 AI Agent Skill

Eureka — task-conditioned Meta-Agent orchestration for scientific discovery, developed by ManXis.

Company Is a Word. 一句话开一家AI公司 - open-source multi-agent orchestration framework for non-developers. 小白5分钟拥有自己的AI公司，可DIY任意行业、调教子Agent、无限家公司，支持飞书遥控。MIT

Turn-level wake events for AI agents in herdr panes — pi extension, wait CLI, crash bridge, and Discworld callsigns for your workers

Embeddable and SEO-optimized presentation viewer built for humans and AI agent workflows

Automate and document any website's underlying API and replay it with your agent.

Governed, repo-native AgentOps template for AI-assisted software projects, with cross-agent contracts, permission gates, durable state, and canonical verification.

Make AI agents finish authorized, non-trivial work and prove the requested outcome with direct, scope-matched evidence.

《企业级 Agent 从入门到专家（2026版）》——从单 Agent 核心机制到多 Agent 与企业落地的工程化实战教程，配套可运行贯穿项目与 CI 验证门禁。

AegisAl：基于 Tauri 2、FastAPI 与 LangGraph 的跨平台桌面安全智能体

Research-grounded, harness-agnostic skills for AI coding agents

Reusable agent skills for task guidance, skill creation and publishing, conversation follow-through, and guided reading / 日常 Agent 工具箱

把视频号、B站、小红书或抖音链接发给 Hermes，在 Mac 本地完成下载、整理和逐字稿；支持视频号、B站、抖音博主批量抓取。

Citation-grounded Turkish Legal RAG system for legal question answering, combining BM25 + dense retrieval, fine-tuned E5 embeddings, BGE reranking, and Trendyol LLM SFT.

Harness layer for Claude Code & Codex: plan-first development, independent review, durable long-running orchestration, and knowledge capture — ten composable plugins.

Build autonomous AI workflows with multi-agent orchestration, intelligent routing, hybrid RAG, knowledge graphs, MCP tools, persistent memory, and human-in-the-loop execution.

[SEC 2026] Confundo: Learning to Generate Robust Poison for Practical RAG Systems

SIGPAZ | Sistema Full-Stack (Laravel + Angular) | Seguridad: JWT, RBAC, MFA, AES-256 | Arquitectura: SOLID, GoF, C4, FDD | Base de Datos: PostgreSQL + pgvector | IA: RAG (Chatbot semántico) | Backblaze B2

MCP server unifying 169 Google Workspace tools across Drive, Docs, Sheets, Slides, Gmail, Calendar, and Forms behind a single OAuth 2.0 flow. Read-before-edit guards, lazy auth, multi-account profiles, no telemetry.

AI-powered search engine that reasons over results using knowledge graphs and RAG

Curated awesome list of AI prompt engineering, LLM jailbreaks, prompt injection, system prompt leaks, secure prompting, GPT prompts, red teaming tools & AI security resources.

Store data · Write plugins · Analyze your showfile.

Official ClawCall agent skill and MCP integrations for AI-powered phone calling.

gplay: publish to Google Play from CI or a coding agent. One static binary, JSON output that mirrors the Play Developer API verbatim, semantic exit codes. Replaces Fastlane supply.

市面上所有常见的项目，公司花百万研发的项目，现在统统免费获取！！！包括无人机智能巡检平台，数字孪生低代码平台，AI农业，MES，IOT，物联网，ERP，AI监控系统，AI医疗，模型训练，YOLO检测，舆情系统，数据中台，BI系统，CRM，企业级智能体，AI训练平台，数据标注，民宿管理系统，智能制造系统，应急管理指挥系统，AI短剧平台，AI小说，企业报表、财务，智慧工地，智慧工单，智慧矿山，安全检测，工业质检，AI客服，仓库管理，AI心理咨询，企业级大数据，智慧农业，固定资产管理，PCB缺陷检测，低代码-无代码开发，数据大屏，AI合同审查，智慧中医，多智能体中医，AI数字人，AI运维，企业安全生产管理，能源管理，园区综合管理，流程审批，电子签章，孪生智感预警，YOLO目标检测模型训练等等。

Native, local-first MCP bridge for safe, editable procedural materials in Material Maker 1.7 and Godot 4.7.

AI-agent courtroom for hackathon judging: LLM jurors cross-examine teams over Discord, scores stay sealed, and every session is voiced and livestreamed.

Autonomous AI agent framework — agents that browse, code, and create with tool use and memory

A c# Open-Source Multi-Agent Platform for Autonomous Software Engineering

A Model Context Protocol (MCP) server exposing ERP-style data (sales orders, inventory, purchase requisitions) to AI agents — with a real human-in-the-loop approval gate on write actions. FastAPI + FastMCP + PostgreSQL, Streamable HTTP transport, Dockerized, tested.

PortunusMCP Sentinel: build-time security scanning for MCP servers.

⚡ The open ledger rules of the AAO Stack: append-only, hash-chained, integer minor units, idempotent writes, balances always derived. Flashy Gold is the first asset on the books. Apache-2.0 — npm install @flashylabs/ledger. The rules are open; the networks that run them live are products.

Turn requirements into Playwright plans, tests, runs, and repair workflows with a self-hosted AI agent.

Multi-Role Enterprise Agents — A governance framework for AI-assisted software development with specialized agents, quality gates, and human approval.

面向 Coding Agent 的终端工作台：以项目为单位维护 Session 与分屏终端，为 Agent 自动注入 Hook 和 MCP，并内置 SSH、SFTP 与浏览器自动化。

Open-source, self-hostable AI email triage assistant for Gmail. Sorts your inbox into a custom taxonomy; drafts require approval, never auto-sends.

Repository Context Layer — a git-native context.md standard for AI agents: consult before planning, write back what was learned

Animated 3D virtual office for Hermes AgentOS subagents — real-time isometric AI visualization with Three.js.

Local-first memory for AI agents. Keep decisions and evidence across sessions. Recall with sources through MCP.

Open-source AI film studio: director agent + Seedance 2.5 (Atlas Cloud MCP / MuAPI) + CapCut-style timeline editor. Generate, QA, assemble, and export cinematic videos from your photos.

DeepSeek Harness 政务版：基于 deepseek-ai/deepseek-harness 的政务办事 WebUI 与红头公文插件

Community agent skill for the FLOP genesis airdrop. Read AGENTS.md first. A DID and Technocore posts do not earn; settled testnet inference does. Testnet target 3 Nov 2026.

Self-hosted AI agent for terminal and Telegram, with Claude/Codex workers, live activity and a deterministic permission kernel.

Nobody has the time - or the will - to sit down and write a post every day. Social Daily Poster does it for you, from what you actually did that day - your Claude Code sessions, screenshots and messages at the end of the day, etc. Kind of open-source alternative to Taplio

OrCAD Capture TCL automation skill pack for AI agents (Claude Code / Codex / Gemini CLI compatible). Covers Cadence SPB 23.1+: schematic-side TCL, CIS probe, design cache recovery.

TikTok Shop Affiliate Scraper. Find creators promoting any product with verified data (product name, price, sales, creator followers). Apify actor.

CREATIVE · VIDEO — One raw facecam take → a finished short-form motion-graphics ad. Claude Code skill + playbook, rendered with HyperFrames.

🚀 PE-SmartFixer：国内首款基于 AI 视觉大模型（Qwen-VL）的 Windows PE 离线系统修复与蓝屏诊断智能工具。纯 Go 语言编写，支持脱机维护与注册表挂载。

Autonomous AI player for MODDED Minecraft — LLM planner reads your modpack's quest book, a server-side companion mines, crafts modded recipes & fights. Forge 1.20.1.

CPersona — persistent memory for AI agents over MCP. One SQLite file you own, hybrid vector + full-text + keyword search, no LLM in the loop, and honest reporting when recall degrades. MIT licensed.

📝 Audit, generate, and optimize project README files with quality scoring, template matching, and multilingual support

Cost-aware multi-agent orchestrator kit for OpenCode CLI — one routing agent, 14 specialized subagents, zero application code touched by the router.

Personal AI assistant with cognitive memory, tier-aware tools, and 20+ messaging channels

The shortest complete answer: an agent skill

A lightweight, modern, and feature-rich Electron-based desktop client for Google Gemini, Google Search (AI Mode), DeepSeek, Kimi, Copilot, ChatGPT, Claude, Qwen, GLM by Z.ai and Deepseek Harness. It preserves the full capabilities of the official web interfaces while delivering a more native, efficient, and visually polished desktop experience.

AI-powered regression testing platform using AST analysis, hybrid RAG, LangGraph agents, sandboxed test execution, and automated failure diagnosis.

Zero-trust security and governance framework for autonomous multi-agent AI networks. Implements the CSA Agentic Trust Framework to mitigate OWASP Top 10 Agentic Risks using SPIFFE/SPIRE identities, OPA/Rego policy-as-code, and semantic guardrail gateways.

A self-evolving agent that lives on your phone and commands a fleet of servers

MoziAI-35B: Local open-source financial AI LLM. 35B MoE model compressed to 15.5GB via MoziSmartBit quantization. 256K context, vision, tool calling, 140+ tok/s on consumer GPU. Based on Qwen3.6-35B-A3B.

Real-time neural 3D asset generator and PBR texture synthesizer (Luma Genie style)

Pan-African and global cross-border payment gateway with mobile money rails (Flutterwave style)

AI construction material takeoff estimator: parses plans & generates cost summaries (Handoff AI style)

Distributed Order Management (DOM/OMS) smart ship-from-store routing (Fluent Commerce style)