Python agents

Local-first kanban for AI-agent workflows. Drag a task to Approved and your AI coding agent picks it up via MCP and drives it through analyst → in_progress → testing on its own. MCP for Claude Code & Cline, OpenAPI for opencode / Open WebUI / Ollama / any function-calling LLM. SQLite + FastAPI, runs on localhost.

Local-first workflow protocol for non-coding knowledge work, decision tracking, and resumable project state.

The cloth between the tool and the model — tool-output thinning and cost observability for Claude Code and Codex. Fail-open hooks, nothing lost.

Using AI to 10x Data Pipeline Dev Speed

MVP to showcase how MongoDB can be used to implement an end-to-end user-facing app

Biologically-grounded runtime for autonomous agent collectives under bounded agency — one codebase runs on a laptop, at the edge, and on OpenShift AI. Three-tier governance, persistent episodic memory, cross-collective delegation, and homeostatic rogue detection.

Prudence, a custom harness powered by Microsoft Agent Framework. Includes a "counsel and craft" mode which delegates executive function to Microsoft Foundry and task completion to local models.

A modular, extensible toolkit for red teaming large language models and NLP systems — covering adversarial text attacks (character, word, sentence, semantic), jailbreak evaluation via JailbreakBench, and prompt injection — with pluggable model targets, automated judges, and clean reporting. Built for researchers and AI safety practitioners.

Private, local-first AI assistant with cited RAG, Ollama, a sandboxed agent, and scoped LAN pairing.

AI-powered company chatbot for answering FAQs, support queries, and business information.

gguf code expert-pruning imatrix moe qwen3.6

Bounded Agents: Delegation Security for Multi-Agent AI Systems - Reference Implementation and Evaluation Artifact

Provide and generate AI agent prompts with industry guides, glossaries, and multi-provider LLM support for scalable, automated content creation.

Lossless wire format for agent-to-agent handoffs. 36.6% fewer real cl100k_base tokens on held-out ToolBench, every byte of decode overhead counted, byte-exact round trip.

Shared HTTP control plane for Chronicle traces and TokenOps spend: one SQLite, one UI. Agents never open the database file.

Self-hosted AI copilot for OpenWrt router monitoring, diagnostics, management and network operations.

Same you, every coding agent.

Cross-cutting design & typography skill engine with an anti-AI-slop doctrine — deliberate, human-crafted type, colour, layout & UI. Referenced by every Chwezi engine.

Local-first, LLM-agnostic memory system — hybrid retrieval (vector + lexical + graph), multi-signal ranking. Runs on 4GB RAM, CPU-only, no cloud.

AI-Psychiatry is a Claude plugin that gives AI coding agents an executive-function layer to detect and control attention drift, overthinking, recursive reasoning, compulsive verification, scope drift, retry loops, deadlocks, livelocks, context waste, and failure to stop after completion.

AgentDeck SDK: the execution layer for agentic software. Agents, tools and workflows as plain Python, with sessions, streaming, events, human approval and run control.

transformers safetensors qwen3_5 text-generation qwen3.5 function-calling

A daily-updated reference of LLM model pricing across all major providers (OpenAI, Anthropic, Google, Mistral, and more)

Minimal, provider-agnostic Python client for large language models, built on niquests.

AI-powered design review, UX analysis, SEO audit, content generation, DevOps & testing toolkit for Claude Code. 12 skills, 12 parallel subagents. One-liner install.

Enterprise AI Business Intelligence platform featuring semantic search, knowledge engine, persistent vector storage, and production-oriented architecture built with FastAPI, FAISS, and Python.

This repository contains SupplyChain-AI: An AI-powered generative chatbot leveraging LLMs, RAG architecture, and predictive analytics to answer conversation queries in supply chain management.

Turn scattered documents into a knowledge base that maintains a position over time. One append-only ledger of evidence-bearing assertions; the RAG index, knowledge graph, OKF wiki and change report are projections of it.

Open-source AI travel planning workspace for evidence-backed itineraries, maps, reports, and printable PDFs.

gguf claudecode agentic unsloth qwen text-generation

A bounded math reasoning agent with Lean 4 verification — conjecture, proof, verified conclusion

让任意 Harness（ZCode/Claude Code/Codex…）调用 OpenCode 作为子 Agent：并行派活、续跑迭代、模型自由——不绑定主 Agent 供应商，可混用 DeepSeek/GLM/Kimi/免费档/Claude 等任意套餐，节省高级模型 token（AI skill + CLI）

AI powered CLI tool to clone and run any repo.

Self-hosted AI Go-To-Market platform: 5 autonomous AI agents for ICP scoring, outreach personalization, deal intelligence, and churn prediction.

Faraday: An Autonomous Web Research Agent (LangGraph/Streamlit). 🕵️‍♀️ Investigates queries using dynamic tools (Tavily, Google, NewsAPI, etc.), gathers multi-source info, and synthesizes structured reports in a Streamlit UI. Features agentic workflow & source tracking.

Open-source AI terminal for China A-shares — stitches the best open-source quant projects (TradingAgents, Kronos, Chronos-Bolt, XGBoost) into one pipeline: multi-agent analysis → predict → verify → WeChat bot. 开源A股AI投研终端:缝合市面最强开源量化项目,预测-验证闭环+微信机器人

Python bridge between MAX Bot API and Hermes Agent. Webhook, Docker, systemd.

An AI-native procurement assistant that turns procurement workflows into natural language actions.

Agentic AI code review for GitLab MRs and GitHub PRs, with the LLM of your choice. Posts only actionable findings as inline review threads.

peft safetensors cybersecurity compliance gdpr rgpd

Multi-AI discussion tool. Claude, Gemini, and ChatGPT debate, discuss, and build on each other's ideas live in your terminal.

🛰️ Autonomous multi-agent AI trading system for XAUUSD (Gold) & BTCUSD on MT5 — quant ML ensemble (XGBoost/LightGBM/LSTM/HMM) + GenAI bull/bear debate + PPO reinforcement learning + live behavioral risk manager. 9 microservices, Next.js dashboard.

safetensors qwen3_5_text tool-calling function-calling agent edge-ai

Self-improving control kernel for AI coding agents (DAGx AGI Kernel): hard approval stops for irreversible actions, evidence-gated completion, self-learning playbook with drift governance. Behaviorally evaluated, harness-portable Agent Skill.

AI Employee (Digital FTE) - 4-tier system replacing 10+ hrs/week of admin | Email, WhatsApp, LinkedIn, Twitter, FB, Odoo, Slack | 10 MCP Servers | Claude AI

Anthropomorphic AI Character Engine: a standardized agent template based on the SPL audit engine for fast, consistent AI character generation. Using causal anchoring and full-logic auditing, it erases OOC, emotional drift and memory loss, offering a stable foundation for AI companions, digital humans, interactive stories, smart customer service and

Open-Source, Workflow platform for AI Agent Swarm Orchestration

Show an AI coding assistant only the code that matters for the change it's making. Measures whether it actually works on your repo.

Adaptive Graph-RAG extending Microsoft's GraphRAG with query-complexity routing, incremental graph updates, and self-verified retrieval to reduce cost and hallucination.

This repository showcases the implementation of a Multi-Agent Research RAG (Retriever-Augmented Generation) Tool built with LangGraph.

面向外贸团队的证据约束客户研究、产品推荐、市场对比、开发材料与可编辑演示文稿 Agent，保留人工审核与独立审批。

Stop searching your documents. Start asking them. Transform Paperless-ngx into a conversational AI assistant using Agentic RAG and the Model Context Protocol (MCP).

Evaluating RAG robustness against corpus poisoning and query-side noise using retrieval and answer-quality metrics.

static region:us

transformers safetensors qwen2 text-generation 25M en

gguf code codeqwen chat qwen qwen-coder

gradio mcp-server region:us

Human-gated Content OS for Chinese social content, with Agent Skills and an explicit production-readiness CI audit.

yeaboi — AI Scrum Master in your terminal: sprint planning, standups, retros, planning poker, 1:1s and delivery reports for your team, plus cost, daily digests and security posture for the AI coding agents working alongside it.

transformers gguf code codeqwen chat qwen

An open-source AI agronomy agent that runs locally on your own machine or server, reaches you on Telegram and WhatsApp, and computes aquaponics system designs from a deterministic, source-cited engineering core instead of guessing them.

Synthelion compresses prompts before they reach any AI model — cutting token usage by up to 70%, reducing API costs, and speeding up responses. It works with any agent or framework: Claude Code, OpenAI, LangChain, OpenCode, Cursor, and more.

Multi-agent information organization workflow for search keywords, outlines, article synthesis, and shareable info boards. 中文：多Agent信息板报生成。

This repository contains a sophisticated AI agent built with LangGraph and LangChain that automates financial analysis workflows. The agent processes financial data from CSV files, performs competitor analysis, and generates detailed reports with interactive feedback loops.

Production-style AI knowledge platform for research papers using FastAPI, React, PostgreSQL/pgvector, Ollama, Docling, hybrid retrieval, cross-encoder reranking, streaming responses, and intent-based query routing.

Autonomous multi-agent DFIR engine with architectural self-correction, cryptographic evidence integrity, and anti-hallucination guardrails. F1=1.00 on 16 synthetic scenarios.

Local control plane that routes engineering tasks across Claude Code, OpenCode, and Codex with real fallback, capability-tier routing, and durable task state.

LLM-driven 2D multi-agent social simulation. A minimal, locally runnable research and educational framework (SD-AgentFoundry-2D). LLM駆動エージェントによる2次元マルチエージェント社会シミュレーション。ローカル実行・最小構成の研究/教育用基盤（SD-AgentFoundry-2D）

论文服务公司多agent架构

The multi-agent coding loop that covers every angle — one model builds, independent AI models review it from every direction, tests decide, you hold the final gate. Privacy-enforced, anti-drift, self-improving.

Self-hosted Personal Agent

Make your browser speak STONKANESE - Turn any Chromium based desktop browser Agentic!

Governance-as-code for AI coding agents: author a policy once, enforce it on every agent (Claude, Copilot, Cursor, Codex) via git hooks, CI, and native controls.

This repository showcases the implementation of a Multi-Agent Research RAG (Retriever-Augmented Generation) Tool built with LangGraph.

AI-native developer collaboration platform unifying team chat, ticket lifecycle, and AI code execution. Two-stage agent pipeline (Planning → Code) with human approval gates, running entirely on local open-weight LLMs via vLLM. FastAPI/PostgreSQL modular monolith, Redis, Qdrant, React/TypeScript, Docker sandboxing.

Open Vibe Architecture (OVA): architecture-as-markdown framework and Python CLI for coding-agent repositories.

新一代（或许）跨平台、可扩展的 python 机器人平台 / multi-platform chatbot platform witten in Python

Enterprise-grade conversational AI platform built with Django REST Framework, Next.js 15, LangChain, and PostgreSQL with pgvector, featuring Docker orchestration, Celery task queues, and production-ready architecture patterns for scalable AI chatbot deployments.

Basic multiple forms of AI usage in PyQt

AIDocSynth liest Dokumente (direkt + OCR), analysiert Inhalte mithilfe von KI und legt jede Datei – PDF, Bild oder Office-Dokument – deterministisch in einem passenden Ordner ab. Versionierung sowie reichhaltige Metadaten sind integriert.

GraphWorkflow is a compile-once engine that executes static multi-agent graphs with substantially lower orchestration overhead than LangGraph.

Autonomous reinforcement learning loop with adaptive hyperparameter tuning, multi-policy ensemble management, and framework-agnostic agent support. Self-converging via exponential backoff. Works with TensorFlow, PyTorch, JAX - bring any algorithm.

AXIOM-02: a deterministic simulation engine modeling high-stakes cognitive dissonance and drive-conflict resolution via a mutual-inhibition drive network. 102 literary & ethical scenarios, reproducible consciousness-complexity metrics. A research instrument — not a claim of machine consciousness.

Autonomous autoresearch framework for Codex and Claude Code, combining experiment DAGs, scientific memory,literature grounding, agentic planning, reproducible benchmarks, and local dashboards.

gguf code agent agentic-coding moe llama-cpp

Use GPT-4 to generate tweets and post them to a Twitter account.

Fine tuned chatbot with OpenAI models

Example streamlit UI to talk to a local llm (for instance run via lm studio)

Prompt Creator – A lightweight Python GUI tool that visualizes project structures and automatically copies code to the clipboard, streamlining the creation of prompt contexts for ChatGPT.

Open Source AI Robot Software for InMoov | LLM + Computer Vision + Voice Interaction | Python | Radxa | NVIDIA Jetson | Raspberry Pi

The .ah (Teleological Semantic Format) skill bundle for Claude Code, Cursor, Trae, Zed & Kiro by David C. Cavalcante. 9 gematria-checksummed skills: coding guidelines, project audit, problem-solving, AI engineering, NPM/Node, content craft, deliberation council & research-grade benchmarking. Token-efficient, always-on after one load.

Multi-key proxy for NVIDIA NIM with a native desktop dashboard — auto-rotation, cooldown, RPM limiting, Claude Code + Codex CLI + opencode support. Free-tier keys pooled behind one endpoint.

AI agent skills for Claude Code and compatible agents — workflow, coding, design, Claude Code meta, media, productivity, and writing

An opinionated workflow system that restructures how product managers work with Claude Code. 16 PM skills, 9 agents, 10 coding rules, 13 slash commands, 6 automation hooks, product brain system, and session lifecycle with memory/handoffs.

Video-analysis skill for AI agents.

LLM Playground - Demo Solution

A production-ready, WhatsApp-native AI agent that qualifies real estate leads, maintains contextual conversations, extracts structured CRM data, and automates follow-ups - handling 90–95% of real-world customer interactions without human intervention.

Benchmarking GraphRAG and AriGraph on MuSiQue, HotpotQA and BabiLong QA1, run locally with Ollama and Llama 3.

A local-first LLM knowledge-base engine that compiles documents into an OKF-conformant, citation-backed wiki

基于孙宇晨长期公开表达形成的战略分析师，帮助普通人重新审视创业、财富、风险与人生选择。