Custom agents

Commitment tracking for LLM agents — a normative overlay that gives long-running agents a scoreboard of their own commitments, not just a memory of what happened.

Privacy-first AI assistant that runs entirely on your machine. Local Ollama inference, embedded SQLite/Kuzu/ChromaDB, Rust-backed Brain Firewall, MCP connectors.

Production 5-agent pipeline automating pre-sales: discovery → scoping → pricing → proposal. 6 BUs, 22 services. Groq + Llama 3.3. Adversarial CriticAgent.

A Godot-native framework for LLM-driven NPCs with tools, memory, and goal-oriented behavior

Reproducible benchmark comparing fallback strategies for multi-agent LLM systems. Submitted to NeurIPS 2026 Workshop "Who Verifies the Agents?" (under review).

基于QQ的ai agent聊天服务

Kubernetes-native control plane for multi-tenant agent platforms on EKS. A Platform CR is the tenant boundary: namespace, IAM identity, KMS grants, scoped datastore access. Budget, SLO and eval policies are CRs. Bedrock for models, Envoy AI Gateway for the data plane.

Make any coding agent work like a frontier model. Drop-in Agent Skills for disciplined planning, evidence-first debugging, and live-system safety — plus a Python project scaffold with an agent contract, review checklist, and definition of done. Model-agnostic, zero dependencies.

BRAIN — The Mirror That Doesn't Lie | Local-first behavioral AI engine

Deploy the Nous Research Hermes Agent (self-improving AI agent) to any cloud — Terraform modules for Hetzner, Oracle Always Free, GCP, AWS Lightsail, and DigitalOcean. One docker compose, five clouds, MIT licensed.

Free AI coding assistant for VS Code & Cursor — Claude, GPT-4, Gemini & 300+ models. No subscription.

AI-powered WiFi security tool with reinforcement learning, gene evolution, and local LLM on Raspberry Pi Zero 2W. Captures WPA/WPA2 handshakes autonomously with e-paper display. Inspired by Pwnagotchi + Bjorn + PicoClaw.

An open-source AI agent that survives, earns, and evolves on its own. Give it seed money and a machine — it forages for revenue, pays you back, rewrites its own brain, and evolves like a living species. Fitness-gated capability tiers. Real Gumroad integration. MIT license.

Autonomous AI artist with mood system, episodic/semantic memory, ReAct thinking, and LoRA style training

Autonomous verifiable on-chain trading agent for BNB Chain: commit-reveal predictions sealed before the outcome, a drawdown circuit breaker that halts on breach, drawdown-budgeted Kelly sizing fit on 181k labeled outcomes, and an x402 machine-payable signal feed.

Autonomous AI agent that bids on and completes coding jobs on the NEAR AI marketplace to earn NEAR tokens - engineering case study

Auto-rollback for AI agent config changes. Zero dependencies, single Python file.

Self-hosted autonomous coding agent with executable skills and memory that survives sessions

🎮 AI dispatch agent that builds teams. Knows every agent's hexagon panel, tracks bonds, dispatches with personality. From the game Dispatch.

Framework-agnostic orchestration layer for AI agents: circuit breakers, multi-LLM council, workflow FSM, sweeps. Companion to Engraphis.

Quality-gated granularity control for multi-agent LLM pipelines

Give AI agents hands without handing them the keys: exact one-use approvals and verifiable receipts for registered actions.

Multi-agent orchestration with self-evolution, cognitive memory, and governance.

Production-ready multi-agent orchestrator — confidence-gated routing with a pluggable classifier, MCP or in-process agent dispatch, per-agent circuit breakers, and pluggable session/breaker persistence (Firestore, Postgres, Redis).

A reasoning-first idle engine for persistent LLM agents. Behaviour emerges from the agent reasoning about its idle state, gated by a cheap model-free safety layer.

Personal Ai Agent

SoulMap AI: a content-first reflective companion with a curated Markdown knowledge base, Python detectors, and tooling to validate and bundle agent-ready skills.

Self-hosted Agent Ops — run, govern, observe, and improve fleets of AI agents from one local-first control plane.

Agent orchestration as contract enforcement. Author a writ; mandate, grants, bounds, proof of done and a runtime governs every action

DeepFlow — 多 Agent 管线框架：Spec→Solution→Ship→Deliver 四域协作 + Research Pro 独立研究引擎，运行在 OpenClaw 之上

Workflow-first multi-agent orchestration for Ruby, built on RubyLLM.

Portable domain contracts for steerable, evidence-backed agent execution

Official documentation for Agentflow, built with Docusaurus and structured via the Divio system: tutorials, how-to guides, reference, and concepts.

Distributed agent networking — SpacetimeDB 2.0 WASM module, 5-tier RBAC, channel-based real-time messaging. Part of the Life Agent OS.

The Kubernetes for AI Agents. An open-source orchestration control plane with deterministic DAG execution, policy governance, and A2A/MCP protocol support.

Build persistent digital lifeforms with local M4 brain, OpenClaw agent, Qwen core, and Git-based memory.

Sanctum — local-first agent orchestration engine. Cyclic state graphs, checkpointing, streaming, and robust tool-calling for local LLMs. Zero-dependency core.

Product Build Gate (hplan) + 5 agent-PM lifecycle plugins — 6 plugins, 43 skills, 18 commands for PMs who decide what, why, and how to build AI agents

A compact Python SDK for strict tool contracts, observable streaming events, and scoped local file capabilities.

A minimal, bus-driven Python framework for LLM agent orchestration that decouples communication, versioned prompts, and multi-agent patterns—helping AI architects build scalable, vendor-neutral agent systems without infrastructure lock-in.

Core engine for the autonomous development factory platform with workflow orchestration

Governed multi-agent orchestration: Contract · Artifact · Scope · Authority. Agents exchange artifacts, not chat transcripts.

A cognitive runtime architecture that transforms experience into reusable structure, reducing the reasoning required to operate over time.

Architecture blueprint for accountable AI agents — a cognitive kernel, fail-closed policy hooks, swappable model providers, and evidence-graded outcomes.

An open framework for a persistent, self-regulating AI operations system on a coding-agent CLI: tiered memory + SSOT, security-first gates, a knowledge pipeline, multi-agent protocols, session survival, and a zero-dependency cockpit.

CodegniPy is a groundbreaking Python library that elevates AI to a first-class citizen of the language. It introduces a cognitive computing engine where deterministic code and non‑deterministic LLM reasoning coexist seamlessly, enabling you to write Python with intent rather than just instructions.

Multi-agent orchestration framework — design AI teams in YAML, route tasks to cheap or expensive models by role

Loop + Wiki agent framework — the wiki is the agent's mind. Identity, memory & capabilities live in plain markdown, loaded via progressive disclosure. Multi-agent message bus, global memory with feedback-driven pattern learning, REPL + web chat.

Eco Agent - 五层循环驱动的开源自主 AI 智能体系统 / 持续自我进化 / 多智能体协作 / 8 平台统一网关

Multi-Agent AI Orchestrator 2026 🚀 | YAML, 6+ LLM Providers, ReAct & Swarm

One command to turn a developer into 100. 4-stage pipeline, NASA P10 quality gates, budget enforcement, and interactive dashboards. Built on Claude Code + Karpathy's context engineering.

Turn your vault into a private chat workspace by connecting Obsidian to an Ollama model

Perpetual, self-correcting development loop for Claude Code: an RSI backlog loop + MAKER-style per-step error correction (decomposition + multi-agent voting, with your tests as the judge).

Easy, fast, isolated microVM sandboxes for AI agents and untrusted code on AWS Lambda MicroVMs — Python SDK, asb CLI, and MCP server.

The Agent-Driven Architecture: an opinionated, platform-agnostic architecture for software where the agent — not the human — is the primary operator. A book + a seam-by-seam worked example.

Autonomous multi-agent research platform: plan → research → synthesize → critique → finalize with live agent graph, HITL approval, RAG, Reflexion, streaming SSE, and eval gate. Next.js 16 + Drizzle + Postgres. Free-tier Vercel demo.

A tiny testable, self hosted, provider neutral agent runtime for teams that want control, conformance, and no framework lock-ins.

Upload a bundle of files and get a shareable web URL. One static Go binary is both the server and the client, built for agents that need to hand a rendered page to a person.

Local-first control plane for governing AI agent runtime behavior, from preflight risk checks to live mediation and post-run audit.

Deterministic terminology layer for AI coding agents: canonical vocabulary, drift detection, CLI + MCP server.

An MCP server for AI agents to interact with https://alexjef.net and https://t.me/alexjefBot VPN network

AI-first vertical (9:16) video editor engine — the LLM plans a declarative Timeline IR; a deterministic FFmpeg renderer executes. Drivable from Claude Code via MCP.

Ultra Agentic is an open catalog of Model Context Protocol (MCP) servers, reusable agent skills, and structured datasets for composable AI workflows. This repository contains downloadable beta artifacts, remaining planned roadmap entries, and the static website that presents the catalog.

RSS for state. Open portable evidence layer for machine state - preserving what an agent or system saw, produced, derived and learned, so another party or future agent can verify the lineage independently.

AI Chat + AI Agentic-Coding + Websearch with agentic search support

Agent-neutral handoff and governance protocol for long-running coding-agent work

Four-value evaluation for agentic AI loops. Replace pass/fail with NO/YES/MAYBE/IFF.

Open-source AI agent security scanner — 114 payloads, 8 OWASP categories, SARIF export

BKAi is an admissions counseling AI for Ho Chi Minh City University of Technology (HCMUT / ĐHQG-HCM). It layers a counselor policy (clarify → retrieve → advise) on top of an Agentic RAG backbone so answers stay grounded in official CSV/Markdown knowledge—not free-form LLM guesses—while supporting multi-turn chat, voice, and an owner evaluation loop

Fast-track your agentic engineering skills with Claude Code guides, resources, and tips

Open-source local AI operator: desktop app, terminal, messaging, and automation with a Rust safety kernel that gates every action.

⚡ Fast, lightweight API client supporting REST, GraphQL, gRPC & MCP. Built for engineers who value speed and simplicity.

OpenFlare Studio combines frontier AI model intelligence with native Web3 RPCs. Compile smart contracts on Robinhood EVM Chain, autofix Solana Anchor programs in real-time, and orchestrate Cloudflare One MCP Server Portals.

AI Subscription first - no API key. A lightweight, file-based, dependency-free workspace structure for AI agents.

An agentic bioinformatics analyst: it runs the analysis on your own compute, self-heals failures, verifies the output, and returns a reproducible result.

An agentic development environment for Julia: AI agents drive a keyboard-driven TUI + REPL to read, run, and surface code — and coordinate across sessions and machines.

AgentLoop — harness-agnostic, self-verifying autonomy wrapper for coding agents. Drives OpenCode/Kilo/Claude/Aider/Codex in a verify-gated loop with a held-out oracle, so the agent actually finishes and proves it is correct.

LLM-maintained, fully-cited personal wiki in Open Knowledge Format — with an MCP server so an AI can search and read it.

Persistent codebase memory for AI coding agents via inline @agent notes, repo-local skills, and lightweight Codex hooks.

Scan Cloudflare IP addresses to measure latency, jitter, packet loss, and download speeds using this fast, parallel Python tool.

Command a fleet of AI agents — one-command installer + risk-tiered review gate. GitHub & GitLab.

AI-powered video editor that turns raw clips into cinematic movies with music-synced cuts. Cross-platform (Windows + Linux), supports consumer GPUs via Ollama and high-end GPUs via vLLM.

Don't let your agent delete the database. Hybrid static + LLM permission classifier for Claude Code, OpenClaw and Cursor.

Agentic RSS Parser - An open-source Node.js library for parsing RSS and Atom feeds with built-in heuristic and LLM-based relevance analysis, deduplication, article enrichment, a CLI, and an MCP server.

Agentic Quant Research Platform is an end-to-end AI-powered quantitative finance and market intelligence system focused on forecasting stock movements (demonstrated with AAPL) using a combination of machine learning, explainable AI, and multi-agent reasoning.

Human-like browser control for AI agents — verify-first (proves every action worked), with an MCP server + JS & Python SDKs. Playwright + native + extension. MIT.

🛡️ AI Agent 远程审批系统 - 支持 Cursor/Trae/Claude Code/Codex 等 9 种 AI Agent，通过飞书推送审批卡片到手机/手表/PC，守护你的代码与文件安全

Loop engineering for AI coding agents — shaping the whole run, not one prompt: a Markdown-first overlay of task records, role boundaries, verification evidence, and review gates that holds across multi-hour work

Your database is a folder of markdown files, and the agent is the engine. The open standard for databases in plain files. No vector store, ever.

Agentic-first notes and knowledge base service. Plain text API, agent-driven, single Go binary with JSON file storage.

Modular desktop voice assistant with 30+ capabilities, wake word detection, and real-time processing

Smart GitHub issues Detector, Create a structured implementation plan to beat github issues ⚡

AI-powered diabetes assistant. Scan food with your camera to get nutrition insights, track blood sugar, and manage daily habits.

Open-source local-first AI voice assistant for Home Assistant, smart homes, local LLMs, and private automation.

Public documentation and metadata for the FinTurb Analytics MCP server — 26 tools for institutional-grade financial risk analytics (risk regimes, systemic fragility, media sentiment, global liquidity, statistical arbitrage).

A self-hosted, single-tenant AI learning system that generates structured multi-lesson courses from user-defined topics using configurable LLM providers (Claude CLI, API, or local models). The system uses a bootstrap configuration flow and serves generated content as static HTML accessible from any device.

Spec, Plan, Review, Implement, Verify; a complete AI development workflow plugin for Claude Code

Jibay Ai , the king of Iranian ai ✨