Python agents

Consistent character visual identity and micro-texture stylizer (Midjourney style)

Agent session replay behavioral audit recorder & anomaly detector (AgentOps)

Agentic machine micropayment escrow settlement gateway (Stripe Agent Toolkit)

transformers safetensors qwen2 text-generation multilingual sea

Sub-100ms conversational turn-taking & barge-in handler (Cartesia Sonic / ElevenLabs)

Sub-100ms conversational turn-taking & barge-in handler (Cartesia Sonic / ElevenLabs)

Deterministic JSON schema extraction and coercing engine for product hardware

Real-time in-memory unified diff & change telemetry generator for live artifacts

Dynamic intent and budget-aware multi-model Pareto router selecting from 70+ LLMs

Cross-border Geo-IP currency converter & dynamic VAT/tax nexus calculator (Stripe Tax)

Reciprocal Rank Fusion (RRF) and hybrid search rank fusion engine

Multi-perspective synthetic consumer focus group simulator for market sentiment

증권사 애널리스트가 만든 한국 상장사 ESG 데이터 MCP 서버 — 5개 기관 ESG 등급·지속가능경영보고서·기업지배구조 지표·온실가스 배출량을 Claude·ChatGPT 등 AI 에이전트에서 바로. API 키 불필요.

Customer lead scoring and interaction velocity evaluator predicting conversions

软件著作权申请材料生成 Skill｜Generate standardized software copyright registration materials with AI.

Query-guided contextual document compression engine pruning irrelevant web noise

E-commerce advertising policy scanner detecting prohibited claims and trademarks

Multimodal visual spec grounding engine calculating physical dimensions and DoF

Long-horizon conversational memory compaction & episodic anchor extractor (Mem0 / LangMem)

Dynamic search synthesis and Page layout compiler generating comparison matrices & HTML UI

Multimodal OCR table grid & merged-cell reconstruction into Markdown (MinerU / Marker)

Dynamic price elasticity of demand calculator deriving marginal revenue maxima

Adaptive token bucket concurrency rate limiter and backoff scheduler preventing HTTP 429 exceptions

Multi-tenant security isolation guard enforcing memory boundary compartmentalization

Minimal JSON Patch (RFC 6902) operational differential engine supporting atomic state sync

Autonomous multi-stage prompt-to-DAG planner resolving dependency topologies

Zero-dependency heuristic adversarial prompt injection & override neutralizer (Lakera / NeMo)

Customer review aspect-level sentiment mining engine extracting satisfaction radar breakdown

Autonomous web browser action planner mapping goals into resilient selector action sequences

A cost-efficient, model-agnostic QQ-group AI agent built around an ~8K-token context window. Powered by NoneBot 2 + OneBot V11, it supports both local and online LLMs through a unified integration layer and extends its capabilities through compatibility with the AstrBot plugin ecosystem.

Alice 集成技能包 · 放进去就能用 · Drop-in skill suite for AI coding agents

Real-time acoustic noise floor estimator and spectral gate suppressing ambient reverberation

Deterministic AST tool-call schema auto-repair & parameter projection guard (AutoGen / LangGraph)

Stateful workflow checkpoint manager calculating state hashes and rollback points

Semantic prompt cache deduplicator calculating Jaccard token overlap to prevent redundant LLM cost

Generative Schema.org Product and FAQPage JSON-LD rich snippet generator

Dynamic session context window tokenizer and dialogue compaction manager

Autonomous web checkout form field analyzer and heuristic autofill engine resolving buyer parameters

Deep research multi-source consensus arbitration engine evaluating authority & contradictions

Deep research multi-source cross-citation graph analyzer and consensus resolver

Multi-agent engine for running a job search — guardrails, human approval gates, and an eval harness. Built while laid off; open-sourced after the offer.

Code for the paper "Emergent Collusion in Long-Horizon LLM Agent Interaction"

Open-source Novgraph client for coding agents: recorded intent, co-change context, ranked blast radius, architecture context, precise code discovery, continuous history, visible context accounting and freshness awareness.

Who Let the Agents Act? is an interactive agentic-security lab exploring how AI agents use tools, access data, and make decisions. Compare vulnerable, prompt-only, and hardened agents to see why prompts are not security boundaries and how authorization, least privilege, data projection, output controls, etc. keep agents safe.

Voice-Agents is a production-ready Python library for building enterprise-grade voice-enabled AI applications. Built by Swarms Corporation, it provides seamless integration with multiple TTS/STT providers including OpenAI, ElevenLabs, and Groq, with real-time streaming capabilities optimized for agent-based architectures.

Curso aberto de engenharia e customização de LLMs em português, do zero à produção, com laboratórios reproduzíveis.

Give coding agents trustworthy, cited answers about your codebase. Code graph + MCP server, no LLM required.

MIT MCP server for Odoo — stdio & Streamable HTTP; search/read/create/write/unlink + custom methods

The job-application assistant that leaves the last word to you: scans the job boards you choose, scores postings against your profile, and drafts answer sheets from your own data. Self-hosted MCP server + CLIs.

Can a decision model beat dedicated rerankers? TypeSafe Jev vs Cohere Rerank 4 vs ZeroEntropy zerank-2 vs a chat-model baseline: 14 datasets, every raw API response, bootstrap ranges on every gap.

⚡ Open-source, privacy-first personal finance cockpit. Bring accounts, transactions, budgets, goals, assets & reports into one intelligent workspace — with optional AI, powerful automation, and self-hosted control. Built to turn scattered financial data into clarity, context and better decisions.

PostgreSQL full-text + pgvector cosine retrieval with reciprocal-rank fusion, bound filters, and a key-free local demo.

Hierarchical episodic & semantic user profile memory graph synthesizer (Mem0)

Autonomous DOM state tree mutation observer & selector healer (Browser Use)

AI agent safety layer for crypto transactions - blocks honeypots, blacklists, and rug pulls before they happen

RAG evaluation and observability lab.

Simple code generator, choose your language and generate code, unit cases and documentation. Built with LangChain and React. OpenAI key required. This is a portfolio project showpiece and will not be updated in the future.

ClawCut-MLX Proxy - A high-performance bridge between OpenClaw and LLM.

ArchiFlow is an event-driven AI agent framework designed for software architecture, development, and code review tasks. Built on a lightweight message queue system, combined with an autonomous agent framework.

Complete alignment and safety architecture for autonomous AI agents. Membrane security, continuous trust verification, epistemic hygiene, emergence protocols, and defence tools. 30 years of cybernetic research — deployable today.

Deterministic runtime for agent evaluation

Transforms MCP tools into collaborative, reasoning agents using modern agent frameworks.

Middleware for simplifying the design, development, and deployment of agents

Peridot v1.5.4 [STABLE] | Sovereign AI Kernel. Offline, GPU-accelerated Llama/Qwen framework. Now with native Linux support. Features 10Hz ZAT-SCS predictive preemption, speculative context streaming, dynamic VRAM arbitration, TurboVec RAG & hardware telemetry. Zero data exfiltration. Absolute hardware control. Engineered by uncoalesced.

This project helps you check your JetBrains AI Assistant quota usage information. 本项目帮助您查看 JetBrains AI Assistant 的配额使用情况。

Fullstack Chatbot using open source LLM (Huggingface)

Runtime Reliability Infrastructure for LLM Pipelines — enforce deterministic rules, measure the Balance Index, and audit every decision.

corporate law RAG system with advanced retrieval and context handling

A Streamlit document Q&A assistant for PDF, DOCX and TXT files, with OCR for scanned pages and TF-IDF retrieval over a FAISS index.

AI cup contest

A web interface for GraphRAG. 🚀

An open-source autonomous AI agent implementation inspired by Cursor Agent, built with the Swarms framework. This production-grade agent can autonomously plan, execute, and complete complex tasks using a combination of Large Language Model reasoning and tool execution.

Harlo — Your AI coach. Built on USD composition semantics for persistent cognitive state management. Patent Pending.

HIAS TassAI Facial Recognition Agent processes streams from local or remote cameras to identify known and unknown humans.

JobOracle is a lightweight CLI tool that combines job-market search, user profiling, and multi-agent LLM analysis to generate practical, personalized employment guidance reports.

An open-source AI that quietly remembers who you are — in plain markdown you fully own. Works with Claude Code, Codex CLI, opencode, and any other agent that reads AGENTS.md.

An autonomous AI agent that collects art

An automated research tool based on Large Language Models (LLM) that can automatically collect, analyze, and synthesize information to generate structured research reports.

An autonomous AI agent that crawls, summarizes, and publishes news articles.🚀

AI-powered chatbot built with Python, NLP, and Flask — automate customer support queries with intent recognition and dynamic responses.

Let Claude work while you play with the cats. Approve or reject Claude Code commands from your Apple Watch, iPhone, or Android — from anywhere, with a single tap.

Creating Bedrock Agents with Streamlit Framework

An AI Agent bulit using dynamic scraping technologies (Selenium) in Python leveraging OpenAI and Ollama APIs!

AI agent for natural language video editing and directing

Deterministic 5-Phase Autonomous AI Engineer with Semantic Code Graph Analysis & Static Data-Flow Tracking.

An AI-powered tool that reads your CV, extracts key details like education, experience, and skills, and automatically builds a professional portfolio website using that data. Perfect for job seekers and developers who want to showcase their profiles fast.

A central intelligence with many distributed agents interacting with the environment independently.

Transform vague prompts into clear, actionable instructions - promptly and thoughtfully

Ask questions in plain English. Get SQL, results, and answers scored by SQLAS, orchestrated by LangGraph, safe by design.

Control Plane Integrity Tool for AI Agents. Cryptographically seal, verify, and audit the markdown files that control your AI Agents.

Python bindings for Cross-Language MCP Orchestrator, think of LangChain + Vercel AI kit but for MCP

Claude Code plugin for Ruby, Rails, Grape, PostgreSQL, Redis, and Sidekiq development

This project is an advanced, locally-hosted AI companion skill for the OpenClaw agent framework. It brings to life Sigrid, a dynamic digital entity designed with deep psychological realism, complex emotional states, and a unique "Heathen Third Path" worldview. Sigrid is built on the Ørlög Architecture.

✨ 基于代码生成和函数调用(function call)的大语言模型(LLM)智能体 ✨ 通过自然语言提问，使用大语言模型智能解析数据库结构，对数据进行智能多表结构化查询和统计计算，根据查询结果智能绘制多种图表。 支持自定义函数(function call)和Agent调用，多智能体协同。 基于代码生成的思维链(COT)。 实现智能体对用户的反问，解决用户提问模糊、不完整的情况。

A dual-mode tool providing long-term memory management for Claude Code and other MCP clients. Features both a CLI interface for direct commands and an MCP server for programmatic access.

A self-extending AI agent built with Google ADK & Gemini 2.0 Flash that dynamically creates, stores, and reuses its own skills at runtime — growing smarter with every task.

🧰 Tool Search Engine for Efficient Tool Use in AI Agents

Fully automated AI presentation system — pre-generates narration, fires live n8n demo workflows, and answers audience questions via voice Q&A. Zero manual input during the talk.

AI agent for processing Google Meet/WhatsApp/Telegram meetings, automating projects management & tasks assignment in Todoist.

Most advanced Flask-based MCP server