Custom agents

🤖 BEBO the PET — An animated AI desktop companion that lives on your Windows desktop. Always on top, always ready. Click to open a sleek AI panel powered by GPT-OSS 120B via Groq. Summarize, humanize, simplify, draft emails, fix grammar & ask anything. Built with Electron + Node.js.

Journal-entry testing AI agent for auditors (ISA 240 / AS 2401). Import a CSV of journal entries, get a risk-ranked review universe + a professional audit report (PDF/Excel). 10 deterministic rules, AI-assisted priority ranking, hash-chained auditor decisions. No-code console; runs locally, free-tier AI.

Agent Skill - March 7th Role-Play Skill

Secure read-only PostgreSQL MCP server in Rust — a hardened alternative to the deprecated @modelcontextprotocol/server-postgres.

Long-session handoff for Hermes Agent: measure how close a chat is to the token limit that ends it, export the whole session, and continue in a fresh chat that reads the parent transcript in full. Recovers context that compaction already removed.

Low-latency in-memory, in-process LLM engine for scalable and real-time inference in Go. Repurposing LiteRT-LM & Gemma 3 for backend systems and Google ADK v2 agents.

AI agent that researches script clearance for film productions - extracts every flaggable item from a screenplay, sources evidence via Parallel, and triages it for human review. Built with Gemini + Google ADK for the Agentic Cinema hackathon.

Real-time desktop floating token monitor and performance telemetry capsule for Google Antigravity (CDP sniffing, 5-segment breakdown, TTFT & tok/s)

A Codex plugin that reduces over-design, hidden failure, and evidence inflation in research engineering.

FinSight：可追溯、可修订的多 Agent 金融研究工作台，支持研究图、可编辑 Skills、原生运行记录与多格式报告。 | A financial research workspace with traceable evidence, human revision and editable agent methods.

Analyze OpenClaw session logs to generate weekly self-improvement suggestions for AI agents without silent modifications.

Agent-agnostic evidence-bound memory and handoff side-car for multi-agent systems. Claims carry checksummed excerpts — verified means re-verifiable, stale evidence gets flagged. MCP server, CLI, and git hooks. Apache-2.0.

Community skills for better UiPath Agentic Automation.

A Home Assistant integration providing a Retrieval-Augmented Generation (RAG) AI agent with configurable backends.

tqdm-style progress bars in the Claude Code statusline for any long-running job. Claude picks how to observe progress; the ETA corrects itself; crashes come back with a skull and a report.

A celld-native AI agent framework — one agent per cell, alarm-paced bounded steps, no platform or model lock-in.

Cad, Webassembly, Typescript, Three.js, OCCT, Drafting-tool, (Autocad / Zwcad)-alternative

Autonomous coding agent built on LangGraph + deepagents. It natively plans, builds, verifies, and ships real production changes with a built-in human-in-the-loop review stage.

Autonomous AI-powered job search that runs locally. Scrapes jobs, scores them against your resume, generates LaTeX CVs, and shares listings via a community network. No accounts. No cloud. 100% private.

Autonomous BareBone Harness that Audits your complete codebase

An AI-powered coding assistant fine tuned for local light-weight LLMS with enhanced features for file management, terminal integration, testing, code refactoring, and project management.

🦾 Portable Jarvis-like AI assistant that runs entirely from a USB drive - 100% offline, voice commands, computer control

Windows release binaries for the Hired Aura desktop app — distribution only; application source is private.

FreeOS — self-hosted multi-user multi-agent AI assistant with modular organization OS (based on Octop + openXYOS)

MCP server for code structure analysis across 20+ languages. Tree-sitter powered. Works with Claude Code and Claude Desktop.

AI-powered conversational sales assistant and e-commerce product recommendation bot built with Python, Gemini AI, and vanilla JavaScript.

Practice technical, behavioral, and system design interviews with real-time AI feedback and scoring

An independent benchmark for the Tiiny AI Pocket Lab. Measures what the box actually does: prefill scaling, sustained throughput, concurrency and reasoning cost, with NPU budget as the currency. Web app plus a self-contained HTML report. Python stdlib only.

Slow and steady wins the (AI) race! 🐢🏁 turtle is a locally hosted CLI LLM coding assistant because F%#@ data-centers!

OMZ — oh-my-openagent 编排能力的 ZCode 移植：多 agent 并行编排、访谈式规划、独立评审与双证据验收。core 默认零侵入，graph/orchestration/dashboard 可选启用。

Portable agent skills and instructions, with an installer for Claude Code, Codex, Cursor, Gemini, and Grok.

AI translation stack for highest quality native translation

Non-intrusive Windows 11 desktop HUD monitoring LLM usage and agent activity across AI coding tools.

一个好用的文件解析skill，支持pdf、work、ppt、图片，一键转成智能体能识别的markdown文本

MCP server for the GoModel admin API — grouped tools with gradual discovery, live docs from GitHub, TTL read cache, opt-in HTTP host mode. Runs on Bun; distroless Docker; auto-releases via CI through gated PRs.

Persistent engineering memory & session-continuity control layer for AI coding agents (Claude Code, Codex, Cursor, Gemini), built on the Model Context Protocol. Scans a repo once, remembers architecture/decisions/changes, checkpoints safely, and hands the next agent an exact continuation brief — so agents stop rescanning and losing context.

An open-source AI infrastructure profiler that connects AI workload telemetry to physical infrastructure behavior and economics.

面向 A 股的日频量化研究与回测引擎，支持传统因子 + ML推理 + Python函数混合策略

A security-conscious, local-first LLM agent in Go powered by Ollama & Model Context Protocol (MCP). Features defense-in-depth sandboxing, tamper-evident audit logging, and MCP tool orchestration.

Open Source Desktop AI Agent Runtime - LLM, MCP, Voice Runtime, and local/cloud models wired into one PyQt6 desktop agent (Ollama + Hermes)

语音驱动的常驻 AI 助手（Windows, Tauri 2 + Rust + MiniMax M3）：四级漏斗记忆 / 子代理 / ask_user / 任务看板

A full agentic loop delivered to your phone

Context-driven valuation bias and halo effects across six multimodal LLMs (companion study to Lee, 2026)

LLM-driven browser agent: observe → plan → act loop on Playwright + FastAPI, live-streamed to a React UI. No agent frameworks.

Lightweight long-term memory retrieval for chat agents using NPMI + Hebbian learning — no vector database or embedding model required.

A cockpit for the agents that write your code.

Relation-aware, calibrated and provenance-preserving context routing for interleaved agent conversations

Cursor for the physical world, Connecting AI to the physical world. 物理世界的Cursor，连接AI与物理世界

Hermetic sandbox executor that returns typed, delta-aware feedback to coding agents (Rust). Parsed compiler/sanitizer/test verdicts + run-to-run deltas instead of raw stdout.

Temporal context, CRUD tools, and automated deduplication for Mem0 OSS + Qdrant. Fixes time-blindness and conflict resolution gaps.

Recursive Language Models for pi: persistent Python REPL with rlm() sub-agent recursion, namespace snapshots and a continual harness (/refine) — as a single extension

Open source runtime to migrate DRF to FastAPI (and more to come) 🚚

Safe Multi-Agent Deployment Platform: pairwise safety analysis for autonomous agents that share a filesystem, clipboard, and OAuth scopes. Every verdict is graded on a four-rung evidence ladder, from docs-only to executed-in-sandbox.

Production-grade multi-agent orchestration on LangGraph — Postgres-backed durable state, dual-mode JWT + Azure AD SSO, per-team isolation, and a team-wide review queue. Advanced (LangGraph) tier of the Multi-Agent Orchestrator Template family.

Ninebrains: one Brain, many thinking arms. Open-source desktop workbench for parallel Claude Code and Codex agents with verification gates.

Control-first, session-connected subagents for Pi

A data platform with an AI agent as its serving layer. Ask plain-English questions and get answers, SQL, and charts from a hand-rolled, LLM-powered multi-agent system on Cloud Run. Underneath (In-Progress): SEC filings → PySpark/Delta Lake → BigQuery.

Multi-agent AI pipeline that generates complete, bilingual (IT/EN) tabletop RPG campaigns as print-ready PDFs. Sample content on the open D&D 5e SRD (CC-BY).

A file-based kanban board that AI coding agents and humans work together, with isolated workspaces and a parallel, model-agnostic dispatch workflow

Reliability Harness v2 for OpenCode CLI — task contracts, least-privilege sub-agents, clean-checkout verification, and a deterministic done-gate. Orthogonal agents (scout/spec-critic/test-designer/lead/verifier/adversary) instead of 3 identical thinking clones. Compatible with Oh My OpenAgent. Not a model swap or 1:1 emulation.

Declarative Answer Set Programming (ASP) models for multi-agent spatio-temporal planning, graph topology, and constraint satisfaction with Clingo & Telingo

Multi-agent LangGraph system that turns a factory sensor alert into a costed, safety-gated action plan.

Local-first multi-agent orchestration — any agent on your machine can be the brain and dispatch to the others (Codex / Claude Code / Antigravity).

One model writes the work, a different one reviews it, and neither decides whether it passed. Cross-provider AI review with verifiable evidence, for DeepSeek Harness/Cordis hosts. 中文文档见 README.zh.md。

Provider-neutral Rust coding agent with user-owned provider/model routing, tools, swarm, MCP, sessions, and cost tracking. Public beta POC. Proprietary.

多 Agent 协作打 CTF 实战手册：协作体系 / 纪律卡 / 技术套路库 / 已判死清单 / 实战复盘

Antigravity-style multi-agent orchestration plugin for OpenCode. 10 agents, 6 patterns, DAG engine with worktree isolation, typed artifact bus, cost tracking.

Spec-driven multi-agent Codex skill pack with /agent-do commands for planning, execution, reviews, security, design gates, and cross-platform coordination.

⚓ Captain AI｜可恢复、多智能体的求职公司筛查 DeepSeek Harness 工作流。灵感来自杰克船长——在萧条的职场里，导航你人生方向、勇敢无畏的导师。

Aria — an open-source AI operating system in your browser: a macOS-style web desktop with a live multi-agent brain (local LLM via WebGPU, real tools, live code execution).

Shared situational awareness for multiple coding agents working in the same repo

An autonomous Windows hardening agent with a local language model. It decides with an embedded model, fixes only what it can undo, verifies every change, and rolls back anything that made the machine worse.

Agent-driven code intelligence engine: Python/FastAPI agent orchestration, Rust/Axum code graph and context compression, plus a React + Vite WebUI. Early-stage, work in progress.

DeepSeek Harness 桌面壳：内嵌 Web UI、引擎自动保持最新、预置 4 个插件、插件装坏能自愈。另有 Linux AppImage / zip 产物（CI 构建，未实机验证）。

Open-source runtime for governed multi-agent AI — define agents, tools and human-approval gates as data (YAML), run under real gates, compiled to LangGraph.

用 ~500 行 Python 讲清楚 AI Agent 是怎么跑起来的 · 零配置即可运行 | A minimal ReAct agent you can run with zero setup

Contextra is a high performance AI context engineering platform built in Rust for document ingestion, retrieval, embeddings, memory, prompt orchestration, and multi-LLM application development.

Describe an AI agent, get a ready-to-run agent home with persona, memory and a growth loop. Build one agent or a whole collaborating team.

One desktop app for every coding agent. Pick the harness per session and any model it can reach.

The "Master Agentic AI" application is a sophisticated Multi-Agent System (MAS) designed to embody the principles outlined in the provided blueprint, "Architecting the Agentic-Inclusive AI." It features a cyberpunk-themed user interface and allows users to integrate their own Gemini API key.

Security-first, lights-out software factory: turns a spec into a hardened SaaS on Secure Vibe Coding OS, drives it through security CI, AI review, and periodic assessment, and maintains it in dark or gray mode.

The official Pinecone Plugin for Cursor

Rust powered, self hosting team of agents each with its email, shared organization and agent memory, shared tools and skills. GrokBot or Buzz idea but with decentralized email access, BYOK and regular OAuth social login.

Virastar — A production-oriented agent skill for Persian academic writing, proofreading, and thesis editing, with support for Persian orthography, academic style, terminology consistency, XePersian/LaTeX, and evidence-aware scientific editing.

Phrontis (原 Knowbase) — 本地优先的 Windows 桌面知识管理 + 日程工具：Markdown 双链笔记、知识图谱、四象限日程、本地 AI 助手(Ollama)、插件市场。100% 本地存储、离线可用、免费开源 | Local-first PKM & scheduling for Windows: markdown editor, knowledge graph, AI assistant, plugins. No cloud, no telemetry.

小语 AI 工作台 - 有记忆/情绪/进化系统的 Web AI 工作伙伴（多模型+文件交付+一键分享）

An undo layer for AI agents. Records what an agent changed through MCP, puts it back, and refuses to let it do the unforgivable unasked.

PhotoMagic：利用 LLM 视觉模型分析 RAW 照片，自动生成后期参数，并通过 RawTherapee 批量输出高质量 JPEG。附带 AI 照片评价、多维度雷达图与前后对比功能。

MCP server and CLI for Turkish vehicle insurance values from TSB, with vehicle-code lookup and monthly archives. Python 3.11+, MIT licensed.

AI Testing Framework using Promptfoo for automated LLM evaluation, red teaming, and CI/CD integration with Jenkins. Supports prompt validation, security testing, custom assertions, API-based model testing, and quality gates for enterprise GenAI applications.

Agent-native CLI for fantasy sports leagues. ESPN first, structured output, self-diagnosing.

SKILL.md-standard proofreading skill — code & document review with real, verified formal-verification backends for C, Python, Rust, Java, and C++

Smart LLM and cloud code optimization tool that cuts token costs by up to 75%. Perfect for AI developers seeking maximum efficiency and lower expenses in 2026.

Bulge-tier Excel financial model factory — every cell live-formulated, every number traceable

DEV.to MCP Server — fast, single-binary Model Context Protocol server for the Forem/DEV.to API. Go + stdio, no cold starts.

Sirius — LLM 驱动的币安合约 AI 交易机器人 | AI crypto trading bot for Binance USDⓈ-M futures: trend strategy, auto risk control, TradFi sessions, Feishu alerts

会「玩」的 AI NPC 智能体框架：七大模块（人设/状态/记忆/规划/工具/对话/反思）+ 两个世界（文字 / Minecraft）+ 六维评测 + LLM-as-judge。228 条自建用例 × 真实模型的全量跑批。

ChaChaChat - A simple, embeddable LLM chat with RAG capabilities