Python agents

gguf heretic uncensored decensored abliterated ara

gguf code agent agentic-coding moe coding

原生 macOS AI 安全智能体：漏洞情报、知识图谱、多语言代码审计与报告交付 | SwiftUI + FastAPI + LangGraph

A deterministic control harness for AI agents. Know when to accept, retry, replan, or roll back.

Verification-first Claude Code harness by a mechanical design engineer — 13 validation gates, trust grades, heterogeneous-model cross-verification, supply-chain INTAKE, claim ledger

Code for 'Will Systems of LLM Agents Lead to Cooperation?' (AAMAS 2025)

Financial domain RAG QA system with hybrid retrieval + self-correction, powered by SiliconFlow Qwen3-8B and ChromaDB | 金融领域 RAG 问答系统，混合检索 + 自我修正，SiliconFlow Qwen3-8B + ChromaDB

Stop replaying the transcript: capsule session state + rolling memory for LLM CLIs (Claude Code, Codex). Measured: −90.3% vs no-cache / −30% vs cached replay at turn 10, reproducible bench. MIT, provider-agnostic.

AI Business OS: multi-agent platform with RAG, OCR, speech & workflow automation. FastAPI + LangGraph + Celery + Flutter. Production-grade, Dockerized

Personal self-hosted AI assistant. Voice control, 120+ tools. Cloud or fully local with Ollama. UI, CLI, TUI. Deterministic (code-driven) orchestration!

Claude skill that builds a permanent memory of your career and tailors an ATS-safe, evidence-backed resume for every job you apply to. 2-click install.

AI-driven incident response toolkit. Reconstructs the full attack path of a cloud or Windows breach, maps every step to MITRE ATT&CK, and stages human-approved containment. AWS · Azure · GCP · Windows. Apache-2.0.

Clarus is a RAG system for maximum retrieval accuracy on religious texts. It combines dense semantic search with multi-agent LLM synthesis to provide scholarly-quality comparative analysis across the Quran (8 Turkish translations) and Bible (English KJVA + Turkish).

Ragworks — a self-hosted, low-code workbench for building transparent, traceable RAG pipelines. Wire up ingestion and retrieval visually, then see exactly what every run did.

Agent-operated outbound sales engine: LinkedIn + email cadence, two-stage ICP qualifier, learning loop. CRM-agnostic (Attio bundled, adapters generated + conformance-tested). Clone it and let your AI agent onboard you.

Recluze is a standalone desktop app, a rust wrapper around bailey's that turns your personal WhatsApp into an AI-powered bot in under 5 minutes

Don't just track your OKRs. Do them. — an OKR Doing Agent for Codex & Claude Code.

AI video editing skill that watches your footage before cutting. Vision model analyzes every frame, scores usability, drops bad takes, reorders by narrative, then renders with ffmpeg. For Claude Code, Cola, OpenClaw. 会看画面的 AI 自动剪辑 Skill——先用视觉模型看懂素材再决定剪哪几秒。

Transform institutional knowledge into Open Knowledge Format (OKF). OKF Studio ingests enterprise knowledge from multiple sources, structures it into portable OKF bundles, builds linked knowledge graphs, and makes knowledge reusable across LLMs, agents, and applications.

AI advisory board as a Claude Code skill + MCP server: verifies every quote word-for-word against public-domain sources, or abstains. Fail-closed fidelity. | Совет советников как скилл для Claude Code и MCP-сервер: каждая цитата сверяется дословно с источником в общественном достоянии, иначе отказ.

Product-strategy workflow you run with an AI agent — idea → analysis → strategy → sprint plan, with living hypothesis/risk/metric registers. Nothing invented; every claim sourced.

The open-source AI firewall for enterprise MongoDB databases. Safely execute live AI agent queries with zero sensitive data payload egress to LLMs.

Turn a topic into a real, verified course — an agentic course-synthesis engine with deterministic prerequisite-ordering and claim-grounding moats.

Autonomous AI security engineer — multi-agent swarm that scans, exploits, fixes, verifies, and attests. Open source (Apache 2.0).

Reliable, resumable, code-driven orchestration for sub-agents and agentic-loops

企业 AI 中台 — 让 AI 连接一切 | Enterprise AI Platform with Agent, MCP, RAG, Plugins

Provides access to over 250+ models inside claude-code , opencode , codex and more. Free. Unlimited.

Saudi-aware PII detection & redaction for LLM pipelines. Checksum-validates National ID, Iqama, IBAN, CR, VAT, +966 numbers, passport & more; evasion-resistant; redacts before OpenAI/Anthropic with PDPL/NDMO audit. Local-first, zero telemetry.

Per-repo memory, outcome telemetry, and a calibrated-confidence gate for Claude Code, with MCP and AGENTS.md projections so other AI coding tools can read its context. Notes survive sessions; success claims need test evidence; your reverts are remembered. Local-only, stdlib runtime.

The self-correcting memory layer for AI agents. Zero-dependency Python memory and MCP server. Supersede, revert, or forget a value deterministically. Verifiable erasure, witness-backed tamper-evident receipts, EU AI Act ready.

The ultimate privacy-first, multimodal data extraction and Local RAG workspace. Transform PDFs, Images, Audio, YouTube, and dynamic Web pages into AI-ready Markdown with 100% local vector storage.

RAG for researchers: page-level citations from your personal library, LLM access via MCP. Ask your entire archive, get answers with the intelligence of leading AI.

Vendor-neutral continuation protocol for AI coding agents. Plain-file project state, stdlib validation, recovery and cold-agent handoff.

AI Web：面向 Web 自动化测试的自然语言 Browser Agent 执行平台，支持多浏览器调度、任务队列与可追溯报告。

A scientific-method lab notebook your AI agent drives — research as a tree of questions and falsifiable hypotheses in plain markdown, with an LLM literature wiki, a task manager, and a local browser GUI cockpit.

Open-source Python agent harness for auditable, cost-controlled LLM workflows with YAML playbooks and MCP server support.

A hands-on, step-by-step workshop for building a Travel Assistant agent on Microsoft Foundry hosted agents with the Agent Framework - growing from a single agent to a multi-agent planner with function tools, MCP, RAG, workflows, and memory. Keyless auth throughout.

Simple OpenAI GPT API reference chatbot, that demonstraits basic turn based chatbot principles.

Перегоняет книгу, курс или подкаст в набор вызываемых Claude Code скиллов. Русская локализация cangjie-skill с тройной проверкой и приёмкой живой маршрутизации.

Every complex task is a Digital Odyssey. A role-playing multi-agent framework based on OpenClaw.

Research framework evaluating retrieval-augmented vision-language models for evidence-grounded medical visual question answering.

gradio region:us

Tử Vi Horoscope MCP Server - a Python MCP server for generating, analyzing, and managing Vietnamese Tử Vi astrology charts with clean JSON output for LLM agents.

四大师并行投研系统 — 段永平/巴菲特/芒格/李录 多视角 AI 投研，叠加 V10 TextGrad 自进化引擎(计算图+文本梯度反传)、18 Skills、确定性金融工具链。面向 OpenClaw/QwenPaw 类 Agent 运行时。

ACP-native multi-agent living group chat — event-driven, agent-agnostic, formally reviewed

Large Language Model (LLM) information redactor that prevents private information from being sent to LLMs from agentic tools by substituting placeholders for private information on outgoing requests and then replaces the placeholders on the incoming responses seamlessly for the agentic tool users.

Open-source API to convert URLs and documents into PDFs, screenshots, Markdown, and structured data.

Autonomous digital mind: 33 asyncio loops, Toltec architecture (Castaneda), identity survives model swaps, runs 24/7 on free LLM keys. One Python file.

Local MCP code-intelligence for AI coding tools: surgical search/read/edit, agent-config version history, path-level access + masking guards, and a multi-project hub.

transformers gguf text-generation zh license:apache-2.0 region:us

An open-ended, agent-driven research loop: proposes ideas, runs real experiments, and writes up the paper — end to end, unattended.

A lightweight Python library for dynamic multi-persona interactions management with LLMs.

transformers safetensors qwen2 text-generation chat conversational

Provenance-aware memory for AI agents.

AetnaMem /ET-nuh-mem/ is agent Memory delivers fully local long-term auditable, proof-ready memory for AI Agents via a 4-tier progressive pipeline, with zero external API dependencies, it supports OpenClaw, install it via pip.

養成型 AI 伴侶框架｜Raise an AI companion who remembers, reflects, and grows with you.

Local prompt-cache economics for LLM agents: split cache reads/writes from input spend, reconcile dollars to invoices, and surface concrete TTL/marker fixes.

面向 AI Agent 的规范化开发 Skill，帮助构建高质量智能体 | A structured skill for building reliable AI agents with specifications, workflows, and acceptance.

Enterprise-grade, multi-tenant, model-agnostic, MCP-first Agent platform.

Autonomous AI agent framework — LangGraph brain, swarm orchestration, Arabic-first, with human-in-the-loop safety.

AI software-delivery control plane for Claude and Codex. Build and review with dependency-aware readiness, scoped execution, fingerprinted evidence, 25 engineering lenses, and human approval.

A scientific calculation and plotting QQ Bot based on Python and CQ-HTTP.

Chat with Github Repositories (w/ multiple filetypes). Provides flexible backend: Select from different Vectorstores, Context Retrieval-methods and LLMs.

Multi-agent LLM trading system implementing arXiv:2510.04787: agents develop grid-trading strategies offline and a low-latency bot executes them on Binance spot. Research implementation under active correction, not for live capital.

Convert documents once. Give agents only what they need — PDFs and Office files to clean Markdown, chunks and local search.

Skill that delegates frontend, coding, review, and image tasks to the local Grok CLI

跨框架 Agent Skills 合集：视频笔记生成、本地识图、Windows 桌面/浏览器自动化，外加 Hermes 语言路由插件。DSH 插件已拆分为独立仓库。

Turn your Claude subscription into a multi-tenant agent API with rate limits, cost tracking, autonomous objectives, and an admin dashboard. Self-hostable, no API key.

Curated collection of agency-style profiles with bundled skills for Hermes Agent

Postgres test DB cloned straight from your production, for AI agents and humans. Real-time replication of rows and schema, copy-on-write clones, snapshots. No seeding, no dumps.

Agent 意图框架 — 把人话翻译成结构化意图+槽位+约束。输入规范化(两阶段) + 三层瀑布式意图识别(Code→Flash→Pro)，80% 请求零 LLM 调用，10ms 内返回。650 测试全过。

Agente de inteligencia artificial en Streamlit y LangChain con Google Gemini para consultas en lenguaje natural sobre inventarios, stock y proveedores en Excel.

Focusing on building both MCP servers and clients using the Python SDK to make sure these three core primitives—tools, resources, and prompts—and understand how they integrate with Claude AI, Gemini AI, Copilot and Grok to create powerful applications without writing extensive integration code.

VoxelSage turns CT scans into actionable 3D insights—automatically segmenting anatomy, quantifying tumors and vessels, generating structured reports, and powering agent-guided surgical analysis.

Open-source, local-first control plane for multi-model AI coding agents in VS Code and MCP: task DAGs, source intelligence, durable context and evidence-based review.

A credential is not authorisation. ACP moves the authorise/refuse decision for AI agent actions outside the model, where prompt injection cannot reach it. Specification, Dafny proofs, and a reference implementation — every claim replays locally.

DSH Math Modeling Team Plugin Pack: 2 role agent presets (modeling-coding / paper) for DeepSeek Harness, multi-folder Git collaboration + vision sub-agent; includes a full run on 2023 CUMCM-C. ｜ DeepSeek Harness 数学建模团队插件包：2 套岗位Agent预设(建模编程+论文)、多文件夹协同+识图子代理，含2023国赛C题全流程跑通示例。

🦙 chat-o-llama: A lightweight, modern web interface for AI conversations with support for both Ollama and llama.cpp backends. Features persistent conversation management, real-time backend switching, intelligent context compression, and a clean responsive UI.

Compile AI agent skills into cheap, fast, deterministic pipelines that run without an LLM in the loop

AI-powered Windows desktop assistant with voice mode, Electron UI, local memory indexing, and system automation.

Deterministic control plane for Codex Agents with typed delegation, durable lifecycle receipts, and journaled writer isolation.

HuntForge 铸猎 —— AI 攻防全链路自主解题 Agent（百度 Agent+ 挑战赛作品）：Claude Code 驾驶舱 + 三通道纪律调度 + 88 条离线 CVE 指纹库 + 33 本通用方法论手册 + 二进制/APK 逆向自动化（bin_triage·angr·jadx）+ 幂等提交与证据门禁

A minimal terminal AI coding agent — LLM tool-use loop with sandboxed file/shell tools

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。

Official implementation of SKILLER: Language-Level Reinforcement Learning for Reusable Skill Extraction in Small Language Models.

Open-source LangGraph + FastAPI starter for stateful AI agent APIs with PostgreSQL/pgvector, RAG, API-key auth, Docker, migrations, and tests.

safetensors llama Arabic English LLM Decoder

gguf code qwen qwen-coder codeqwen text-generation

把学校规章、培养方案和公告变成能提问、可追溯到原始文件与页码的大学 RAG 知识库。

Persistent memory for Claude Code. Survives compaction and session boundaries: anti-patch reconcile-on-write with LLM-judged de-duplication, a forced PROGRESS.md handoff, a live PLAN.md anchor with an enforced directive ledger, FTS5 search, MCP tools and a GUI. Pure stdlib Python, zero runtime dependencies.

Self-hosted Qwen3 retrieval server with Embedding, Reranker, MCP, and Web console.

All in one memory system for your harness

transformers safetensors llama text-generation arxiv:2406.04151 text-generation-inference

DeepSeek Harness 成年人(18+/adult)互动叙事 Skill：NPC 活人感（有记忆/立场/底线）、自带破甲与张力引擎、随机开局可预锁、时间推进、全维 YAML 存档。仅限虚构成年人。

static region:us

🚀 AI-powered freelance gig aggregator MCP server for Claude Desktop. Search gigs, generate proposals, negotiate rates & optimize profiles with ChatGroq AI.

Auditable memory layer for AI agents: zero-LLM-call local ingest (~10ms/msg, air-gapped), matches Mem0 on accuracy at ~1000x lower ingest cost, bi-temporal belief-state, MCP server. Honest LoCoMo/LongMemEval benchmarks. Open source (Apache-2.0).

Local-first AI character companion framework: emotion × energy × affinity state machines, built-in memory pipeline (facts, vectors, day summaries), background reflection, and proactive speech after silence—architecture-first “persona bones,” not prompt-only chat. Electron/Vue + FastAPI; optional VLM & TTS. AGPL-3.0.

A股多智能体量化投研系统 | 5 Agent深度分析 + 多空辩论 + 决策复盘 | React股票站 + Streamlit + Windows桌面 + iOS | 免费AkShare/腾讯行情数据源