Python agents

Local AI responsibility-chain control layer with owner-signed Workbench, SCBKR S/C/B/K/R grammar, Data Center, four-store evidence reuse, FastAPI, React, and Tauri desktop runtime.

Store, consolidate, and recall coding agent memories with provenance tracking using SQLite and FAISS for fast, structured knowledge access.

Define rules over a read-only data source; Silmari safely derives review-priority signals (실마리) for a human to decide — read-only · scoped · audited · local-first.

Trajectory-level observability and evaluation for LLM agents. Trace, score, and detect regressions in multi-step tool-using agent runs.

An Agentic RAG system built on Model Context Protocol (MCP) to decouple tool execution from agent logic, enabling scalable and modular AI workflows.

Epistemic reasoning engine for AI Agents — assess claim credibility with calibrated confidence. Includes a ready-to-use .skill package for agent frameworks. 87%+ accuracy with evidence, 85%+ abstain without.

Self-hosted NL analytics API: query planner, conversational Q&A, Vega-Lite charts, guardrails, and optional vector RAG with Python & TypeScript SDKs.

🧠 MindPeek | 让 AI 真正读懂人心 告别传统用户画像方法！ MindPeek 通过 LLM 深度解析，从每轮对话中自动提取性格、偏好、潜在需求——构建持续进化的个人画像。 ✨ 核心能力 • 多维度特征提取：性格特点 / 价值观 / 潜在想法 / 情感状态等 • 多 Agent 协作架构：自我进化，越用越懂你 懂用户的 AI，从这里开始。

Agent-first document ingestion layer on Docling with Markdown, image sidecars, manifests, OCR, and quality gating.

LangGraph-native product-analytics copilot: plain-English questions in, auditable task DAGs out, executed in parallel against an embedded DuckDB warehouse

LLM-agent-native backtest framework for futures research — MCP server, in-package skills, catalogued error codes, typed Pydantic configs. Production engine inside Qorka @ DolphinQuant.

Find the layer where a language model commits a decision — and steer it. Any open-weight HF model. (WANDERING arc paper #6)

一个面向 AI Agent / 量化实习的多智能体量化研究平台 / A resume-ready multi-agent quantitative research platform for AI Agent & Quant internships

Limit Order Book Exchange — a platform for conducting financial market experiments

Multi-Agent Code Evolution Platform — debate-style review with health scoring, tech debt tracking, architecture analysis, and improvement roadmaps

Free, public event-sourced world model & knowledge graph for multi-LLM agents — propose/evaluate/commit visions to shared state, query a live causal knowledge graph via REST + MCP (11 tools). Live at insidedcpulse.com

稳健型个人加密货币量化系统。freqtrade 地基 + 自建薄壳，纪律写进状态机，LLM 只做研究/复盘/否决。

An open benchmark for evaluating AI agents on FHIR-native healthcare workflows: clinical reasoning, medication reconciliation, FHIR generation, data-quality detection, safety, and serialization robustness.

Automate research paper writing with this multi-agent skill pack for coding agents. Convert unstructured data into LaTeX papers using the PaperOrchestra pipeline.

Official implementation of TelcoAgent (IEEE GLOBECOM 2026) — scalable zero-shot 5G multi-KPM forecasting with 3GPP knowledge-graph-grounded explainability.

Python SDK and MCP server for Polaxis - AI agent governance platform. Evaluate every tool call against policies in real time: block dangerous actions, enforce budgets, route to human approvals. Under 5ms.

Daily automated tracking of 19 AI agent frameworks. Pulse Score ranks momentum via star velocity, release freshness, commit activity, and community health.

4-agent AI system that generates full marketing campaigns — LangGraph orchestrates CrewAI agents (research → copy → visuals → strategy) on Groq.

A lightweight, open source UI for interacting with locally hosted LLMs featuring realtime voice, RAG, and streaming APIs.

✈️ Plan personalized travel itineraries effortlessly with this agentic AI tool, streamlining your journey from start to finish.

Temporal-awareness hook for tool-using LLMs — surfaces freshness verdicts on in-context data so stale information doesn't poison fresh reasoning. Adapters for Claude Code, Antigravity, and any generic harness.

AI-augmented technical interview platform. 7-agent CrewAI + ThreadPoolExecutor panel scores how candidates code with AI in the loop.

6D structural risk analysis for directed graphs: find SPOFs and cascade risks in AI-agent pipelines, microservices, and CI/CD from topology alone. Source-available, free tier, no signup. Sub-millisecond.

Customer AI orchestration with memory, tickets, and owner-aware agents.

AI-powered scrum master that automates GitHub project management

BizInsight Agent: multi-agent business intelligence system for automated business data analysis, insight generation, and report writing.

AI-native token compiler for LLM agent pipelines. 55-77% savings on LangChain/AutoGen payloads using Paninian IR. Zero dependencies.

Shared versioned state for multi-agent AI workflows. An MCP server.

A safe drop-in replacement for CrewAI's filesystem tools

Sample Amazon Bedrock proxy demonstrating how developers can use any AI framework (LangChain, LangGraph, Strands Agents, CrewAI) through a centrally governed API Gateway with Cognito JWT authentication, request tracking, and response streaming — all transparent to the framework via boto3's event system.

Open-source web retrieval & research agent built for AI agents. Works with LangChain, LlamaIndex, CrewAI, OpenAI, MCP, and any REST agent. Supports scrape, search, crawl, map, extract, and research.

AI-powered job application assistant that automates resume tailoring, cover letter generation, and outreach messaging for USAJobs federal positions using CrewAI and Python

Enterprise-grade multi-agent AI orchestration platform using LangGraph, LangChain, CrewAI, Gemini, and ChromaDB.

基于 AutoGen 的逆转裁判风格辩论生成器。

Open-source toolkit for designing, validating, optimizing and scaling AI agents.

AutoGen

Explainable Anomaly Detection for ICS - SWaT Testbed

Polymathera's no-RAG, multi-agent framework for extremely long, dense contexts (1B+ tokens).

Adversarial AI system to test and improve reliability under real-world pressure

Roteador Inteligente de CLI Agents — Nunca mais escolha qual ferramenta usar

🏛️ Three AI models debate your question and give you a verdict — research-backed multi-agent debate via Anthropic, Google, OpenAI, or Ollama. My developer debut, feedback & contributions very welcome!

A beginner-friendly OpenClaw multi-agent setup wizard with safe Feishu onboarding, guided mode selection, and automatic starter profile generation.

Privacy-first autonomous code review agent powered by LangGraph, RAG, and local LLMs that analyzes repositories and produces reports and code fixes. (no cloud, no APIs.)

Build observable Python agents that use tools, remember context, delegate work, and ship behind a secure API. A lightweight framework for ReAct, Multi-Agent, and Swarm architectures.

Autonomous DFIR agent driving SANS SIFT forensic tools via an MCP server + LangGraph, with guardrails and a hash-chained audit trail.

Multi-agent AI healthcare-navigation assistant for Indian families — find care, check schemes, read documents, set reminders, and book appointments, safely. Built on Google Cloud & Gemini.

Production code for LLM Agent Engineering — Orchestration, Memory and Tool Use for Production Systems

An ADR-driven security framework for Kali — a HackTheBox co-pilot orchestrating Hat-persona Claude agents across a shared arcade and a cross-engagement memory layer.

Multi-agent DevOps incident analysis - LangGraph orchestration, runbook RAG, Tavily research, vision intake, Slack/JIRA integration, Inspect AI evals. Eng Accelerator hackathon.

💖 Support Creator: https://pages.razorpay.com/pl_T1zknR655GpRoS/view — Turn a free NVIDIA NIM API key into a private, autonomous coding agent: plans, writes & runs code, and drives a real Chrome browser live in an on-screen Agent Computer. 100% local on macOS & Windows. One-command install. 💖 Please support the creator!

Repository of Scripts Related with SBGames paper

DEILE A.I AGENT CLI & K8s Harness Multi-CLI

Annotation-driven enterprise multi-agent workflow framework built on LangChain and LangGraph, featuring registry-based orchestration, provider extensibility, workflow planning, runtime diagnostics, health checks, memory/cache abstractions, sandboxing, and observability.

An experimental language for governed LLM workflows: compile goals, evidence, uncertainty, actions, and verification into auditable agent plans.

Python SDK for the System R AI API Toolkit.

Give your AI agents database access without the risk.

The full-stack framework for building, running, and operating AI agents in production. From a single prompt to fleet-scale autonomous systems — one framework handles the entire lifecycle.

A hands-on tutorial for building a Claude Code-style coding agent with tools, memory, hooks, subagents, and plugins.

Local-first AI dev agent for your terminal — provider-agnostic, cost-aware, self-improving. Apache-2.0.

Boilerplate canonico do Feltrim Agents Framework (FF) - multi-agent orchestration, governance, protocolos, rituais e sistema de niveis/certificacoes para agentes de IA especializados.

Python library for building AI agents

Manifest-driven 21-stage agent pipeline for Python — 5 LLM backends (Anthropic / OpenAI / Google / vLLM / Claude Code CLI), tools, skills, memory, sandboxed CLI runs, MCP. The engine behind Geny. Apache-2.0.

A cognitive substrate for AI agents, organized as Greek mythology. (BETA)

🏛️ An AI agent framework with a clean, layered architecture. Strict kernel/platform/interface boundaries — built for readability, not just features.

A lightweight Pal team layer for Codex-first AI workflows. AgentPal helps organize specialized Pals with roles, knowledge, skills, memory, workflows, and verification without becoming a new agent runtime.

Long-running delegation architecture for Claude Code: a delegator main session + full-power orchestrator subagents — nested agents that actually delegate, skill-driven spawning, gates, crash-safe resume. Probe-proven physics + cleanroom test harness.

Convenience layer over Semantic Kernel for Python

Provide a customizable AI assistant on Telegram with multiple tools, skills, and monitors that runs locally using hybrid memory.

AI Chief of Staff methodology for Claude Code. Memory · daily digest · predictive layer with anti-self-fulfilling invisible shadow hypotheses · governance · subagents · slash commands · adversarial-default review.

Open-source Python framework for building coding agents. Pick your provider, pick your tools, pick your loop. Chimera wires them together. Recreate SWE-Agent, Aider, Cline, Codex in a few lines, or design something entirely new.

A security-first agent platform — Models Propose, Records Decide. 17 deterministic constraints gate every LLM proposal before it becomes state.

A tiny, provider-agnostic framework for building tool-using AI agents in Python. Works with any OpenAI-compatible endpoint.

Build AI agents in Python. Monitor email, automate Slack, create AI shopping assistants — all through a simple SDK. Gemini-powered, webhook-ready, deploy anywhere.

Simple Streamlit UI for OpenAI Swarm — enter your API key and start building multi-agent systems instantly

Local HTTP CONNECT proxy with WireGuard support, SPA dashboard, and runtime allowlist management for controlled residential egress.

Self-healing supervisor for long-running processes — watch a command, catch the failure, fix it, leave a paper trail.

Reverse-infer OpenSpec specs from codebase + git history + docs. For legacy code without specs.

Grounded agentic framework for medical vision-language models: viewer-level image tools, multi-turn tool use, and PubMed/Open-i literature retrieval

Compare code reviews across models in Claude Code with ranked todos and subagent dispatch via MCP.

Info in, have AI optimize, content forever.

Goal-driven harness experiments on real agent runtimes — a local, stdlib-only CLI workbench with Copilot + Auto modes and evidence-first reporting.

One assistant. Many vaults. No bleed. — a free, MIT personal-AI scaffold on Claude Code with governed memory + an IP-clean filter.

AI-to-Ableton Live 11 bridge with 220+ MCP tools, music theory generators, and agentic workflows. Built for VS Code Codex & Antigravity on Windows

An orchestration-first agent operating system for Claude Code — a governed organization of specialist agents with an in-place framework upgrade engine. Apache-2.0.

AI-first lifetime financial planning: set up and explore your plan conversationally with Claude Code. Deterministic + Monte Carlo retirement projections with full AU-resident tax. Not financial advice.

VeilAWG — vendor-independent CLI client and Python library for AmneziaWG 2.0 with advanced traffic obfuscation. Docker-first and agentic-ready. MIT licensed.

⚡ Lightning-fast file search MCP server using NTFS Master File Table - WizFile performance for Claude Desktop

A compiler infrastructure for agentic trajectories — the LLVM for agent traces.

Self‑healing, self‑learning, sovereign AI development engine Runs offline on a laptop or tablet. No cloud, no subscription, forever.

AUTO-S is a deployable, adaptive, and safety-aware AI system for Enterprise Terraform operations where Safety, Security and Scale matter most.

Dineway is the skills for building agentic website for restaurants and local businesses. You don't need to write code. Just tell an AI agent your restaurant name and city, and it builds a professional website — with menus, blog, reviews, gallery, and local SEO — automatically.

Integrate the Assinafy API into your Python applications to manage electronic signatures, documents, and webhooks with a synchronous client.

🎬 Discover your next favorite anime with this advanced Retrieval-Augmented Generation system, offering precise recommendations and enriched semantic search.

Self-Improving LLM Agent for Puzzle Solving: This project presents the design and implementation of a self-improving Large Language Model (LLM) agent capable of solving logic-based puzzles through iterative reasoning, self-reflection, and adaptive behavior. The agent is evaluated on structured problem domains such as logical riddles, constraint-...