Python agents

Open-source AI work assistant. Connects to Gmail, Slack, Calendar, Notion, Linear and GitHub, runs autonomous scheduled workflows, and remembers what matters. Self-hosted, provider-neutral.

AI film preproduction Skill for Codex: reference-video analysis, scripts, detailed storyboards, visual assets, Seedance 2.5/2.0 prompts, and verified releases.

Parent-operated Hermes profiles for children in WisdomForge bands 5–10, 11–14, and 15–18. Fresh profiles only. Not a kids-AI product.

Final Year Project of Bachelors of Science (Computer Science). A Voice-Enabled-Urdu-Chatbot build using RASA specifically designed for farmers in Pakistan, they would be able to talk to Chatbot in Urdu Language and get to know the weather forecast for next week, Machinery prices, Fertilizers and Pesticides prices in Urdu Language.

📚 LangChain Deep Agents 课程式学习项目(deepagents + DeepSeek):minimal-deepagent 基础课(最小智能体→工具→多轮对话→记忆→多智能体→生产化)+ advanced-deepagent 进阶课(组件原理+中间件/Backend/编排/生产化)+ 生产级个人助手综合实战(SaaS 多租户+述职报告自动化)。每课一个可运行示例+中文注释。

Turn RAG system evolution into solution packages you can review, port - and reject. Two independently adoptable design packages (knowledge compilation / governed improvement), 40 claims with evidence coordinates, contracts, governance gates, D0-D5 handoff. Docs only: no runtime code, no unverified benefit numbers.

Curated list of DeepSeek Harness (DSH) plugins for 2026, with quality check.

🫀 The autonomous heart of your GitHub repo — 24/7 AI agents that triage issues, review PRs, repair CI & keep docs fresh. Runs entirely in GitHub Actions. No server, no database. Provider-agnostic: Claude, OpenAI, Gemini & more.

transformers safetensors qwen2 text-generation verilog conversational

Model Optimizer safetensors qwen3_next nvidia ModelOpt Qwen3CoderNext

Agent-native research workspace. A deterministic CLI that ingests arXiv / PDF / LaTeX / Zotero papers into an Obsidian-compatible knowledge graph, with local hybrid search (BM25 + vectors), claim-level provenance, and a nightly literature radar.

The company brain: it remembers, thinks, and does the work. Meetings become a typed graph with sources — it answers with citations, spots divergence on its own, and returns reports, automations and specs for AI executors.

Built as a free-time side project at Consultadd — in the spirit of Gmail's origin as a 20%-time project at Google. Not an official company product (yet), just one engineer's attempt to fix a problem every team has.

A Python engine for Pokémon TCG simulations and bots

RAT: RunAnyThing via Fully Automated Environment Configuration (EMNLP 2026)

Multimodal video dossiers for agents: transcripts, frames, OCR, evidence, and RAG-ready knowledge.

A transparent same-protocol LLM proxy that routes cheap tasks to Flash and hard ones to Pro by structural signals — no keyword guessing.

Subscription window keeper that keeps AI coding plan windows active, locally or via a remote server.

Open-source legal AI assistant with local RAG — search laws, chat with citations, analyze document

Zotero → Markdown 语义文献包 → 向量检索 · 本地文献流系统 · MCP 服务

Full local control of your Zotero library — from your terminal or your AI agent. No cloud, no API key. CLI + MCP server + bridge plugin.

网友红领巾的公考决策、复盘、选岗与来源核验 Codex Skill

CPersona — persistent memory for AI agents over MCP. One SQLite file you own, hybrid vector + full-text + keyword search, no LLM in the loop, and honest reporting when recall degrades. MIT licensed.

Dynamic Agent-to-Agent (A2A) task graph generation, subtask independence verification, and parallel multi-agent orchestration

Heurisko is an autonomous AI research assistant and academic search engine powered by multi-agent AI, offering deep document intelligence, conversational research, and real-time streaming capabilities.

Dynamic Multi-Layer Code Flow, Instant Semantic Call Tracing, and Interactive Architectural Navigation.

transformers safetensors qwen2 text-generation conversational en

Long-running Telegram agent on MTProto: durable runs that resume after a crash, markdown/JSONL canon instead of a database, and a subscription-backed LLM relay in Rust

MCP server bridging Google NotebookLM with Claude Code/Desktop, Cursor, Cline, Continue. Cookies-from-Chrome bypass, auto-refresh, 27 tools.

Intelligent Product Management Assistant - v1.0

Self-hosted alternative for Grok Bot

transformers safetensors pebble_25m text-generation pebble language-model

gguf llama.cpp qwen3_5_moe kat-coder kat-coder-v2.5 qwen3.5

safetensors jais Arabic English LLM Decoder

Claude Code IDE integration for Sublime Text 4 — in-editor diff review, live selection context, @-mentions. Speaks the official IDE protocol (WebSocket/MCP). Unofficial community plugin.

meow — Nine Lives exoskeleton for Claude Code. Owns the session boundary: birth, exit contract, rebirth. Bun heartbeat + Python governor + markdown roles. 30 verifiers, all green.

Explainable disease prediction using multi-model scikit-learn, FAISS RAG, and a modern Flask UI.

Production-grade hybrid RAG: BM25 + dense retrieval + cross-encoder reranking + LLM-as-Judge

A benchmark for evaluating LLM agents as sequential hyperparameter optimizers across 30 executable machine learning tasks

GenPark AI Agent Skill - Dynamic mock object synthesizer and behavioral fuzzer generating contract-conforming test doubles for agent tool sandboxing.

RLE: harness × model benchmark on a live RimWorld colony. Swappable agent harnesses (Felix multi-agent, coding agents over MCP, or your own plugin) are scored identically against an unmanaged baseline. FLE for multi-agent coordination under uncertainty.

In-flight circuit breaker & loop recovery for LangGraph, LangChain, OpenAI & Anthropic agents. Catches reasoning loops, prevents runaway LLM costs with budget hard caps, and auto-injects Reflect & Pivot prompts.

Open-source, evidence-informed baby & toddler sleep consultant (Agent Skill) — helps from conversation alone, sharper with recent sleep history; constraint-aware, safety-first, never diagnoses.

A 4-step multi-agent RAG system (preference understanding, semantic alignment, contextual summarization, ranking) leveraging user watch history, mood, and movie metadata; deployed via Streamlit UI and evaluated using NDCG@5 and HIT@5.

An AI agentic operating system for mixed reality on the Meta Quest 3 — your own J.A.R.V.I.S. Multi-agent orchestration, multimodal perception (sight/hearing/gaze), 42 holographic widgets, 20 LLM providers.

Intent-agnostic multi-agent legal assistant: planner, hybrid retrieval, and a rule-based citation-verification gate that abstains when it cannot ground a claim. Strands Agents, Bedrock, AgentCore Runtime + Memory, Guardrails, OTEL, CDK.

Turn a business's scattered data into a queryable knowledge graph — and plug it straight into Claude. A macOS CLI and Claude Code skill, built on graphify.

Production-ready cross-border e-commerce multi-agent system built on AgentScope 2.0 with DDD onion architecture, GatewayThrottle, semantic cache, stream queue, and two-stage retrieval.

AI 教材数字化与互动辅导平台：PDF/扫描教材经 MinerU OCR 结构化出题，文本 + 视觉双模型审校与确定性质量门禁；学生端七种题型互动、分层提示与错题多轮陪练闭环；FastAPI + PostgreSQL JSONB + React 19

A multilingual Agent Skill Pack that turns AI agents into guided learning coaches.

AI-powered B2B lead finder: discovery on licensed lead data, LLM fit qualification with the reason written out, CSV out. The finder core, extracted from OpenOutreach.

Python Framework for Multi-Channel AI Assistants and Agent Applications

MCP server for the Neural DSP Quad Cortex — build, edit and control presets and scenes from Claude or any MCP client, over the reverse-engineered USB-HID protocol. macOS + Windows.

ATLAS — industrial Agentic RAG platform (LangGraph): routing, query decomposition, Corrective RAG, Self-RAG reflection. FastAPI + SSE, pluggable vector stores, auth, rate limiting, tracing, Docker, CI. Academic webinar kit on archive/academic-labs branch.

Async-LLM is an architecture that improves LLM task execution by planning, scheduling, and executing subtasks efficiently, inspired by how compilers optimize programs.

Cooperative Multi-Agent Reinforcement Learning (MARL) Shapley value credit assignment engine evaluating fair marginal agent coalition rewards.

Cooperative Multi-Agent Reinforcement Learning (MARL) Shapley value credit assignment engine evaluating fair marginal agent coalition rewards.

Burrows-Wheeler Transform (BWT) and FM-index compression engine enabling ultra-fast exact substring and genome read mapping in sublinear time.

Hybrid Logical Clock (HLC) distributed causality coordinator maintaining monotonicity and bounded physical drift across unsynchronized network nodes.

Saga Pattern orchestrator coordinating forward steps across microservices and autonomous agents with automated compensating reverse rollbacks.

Information-theoretically hiding and computationally binding Pedersen vector commitments with additive homomorphic properties over prime fields.

Groth16 zk-SNARK verification equation solver evaluating bilinear pairings and public input polynomial combinations.

Go-inspired M:N work-stealing runtime scheduler with local runqueue deques, victim work-stealing, global queue fairness, and cooperative goroutine preemption.

Lehman-Yao B-link tree concurrent index enabling lock-free read operations across dynamic node splits with high-key right links.

Exact Variable Elimination inference engine for discrete Bayesian Networks computing conditional posteriors and marginal probability distributions.

Saga Pattern orchestrator coordinating forward steps across microservices and autonomous agents with automated compensating reverse rollbacks.

Bentley-Ottmann sweep-line algorithm detecting all pairwise line segment intersections in 2D Euclidean space.

Conflict-Driven Clause Learning (CDCL) 2-Watched Literals (2WL) clause indexer accelerating Boolean constraint propagation.

Self-Consistency majority voting engine aggregating multiple stochastic reasoning paths to extract high-confidence consensus solutions.

Production-grade genpark-flatbuffers-zero-copy-vtable-serializer-skill skill for AI agents

Shapley-Scarf Top Trading Cycles (TTC) algorithm for Pareto-efficient, core-stable, strategy-proof indivisible resource allocation.

Wesolowski Verifiable Delay Function (VDF) modular exponentiation evaluator and O(1) non-interactive Bézout proof verification engine.

Multiversion Timestamp Ordering (MVTO) concurrency control engine supporting non-blocking reads and Thomas Write Rule serialization.

TransE multi-relational geometric knowledge graph embedding engine representing relations as translations h + r approx t in continuous vector spaces.

Chandy-Misra-Haas probe-based edge-chasing algorithm detecting distributed wait-for dependency deadlocks across asynchronous agent swarms.

Strict Two-Phase Locking (SS2PL) concurrency manager with shared/exclusive lock upgrades and DFS wait-for graph cycle deadlock detection.

Datar-Gionis-Indyk-Motwani (DGIM) streaming algorithm for estimating frequency and bit counts over massive sliding windows in logarithmic memory.

Named Entity Disambiguation (NED) collective coherence graph ranker linking ambiguous text mentions to unambiguous knowledge graph entities.

Distributed Write-Ahead Log (WAL) and LSM segment cleaner compacting tombstones, eliminating stale updates, and reclaiming disk space.

Counterfactual Regret Minimization (CFR) game theory solver computing Nash equilibrium strategies for extensive-form games and poker scenarios.

Reed-Solomon (k+m) systematic erasure coding kernel over Galois Fields GF(2^8) tolerating up to m disk or network shard dropouts.

Dynamo-style consistent hash ring with virtual nodes (vnodes) and binary search bisecting for balanced partition key allocation.

Production-grade genpark-capnproto-word-aligned-message-arena-skill skill for AI agents

Consistent hashing ring with virtual node replication for balanced distributed key partition and minimum remap churn.

Strict Two-Phase Locking (S2PL) lock manager with shared and exclusive lock modes, lock upgrading, and atomic end-of-transaction release.

System R Selinger dynamic programming cost-based optimizer determining optimal join orderings, access paths, and cardinality estimates.

Rigid virtual structure formation controller mapping leader-follower affine transformations, rotation matrices, and geometric keeping.

Algebraic topology simplicial complex engine computing chain groups and boundary matrix operators verifying d^2 = 0.

Production-grade genpark-aries-wal-crash-recovery-engine-skill skill for AI agents

Marching squares and cubes isosurface extraction engine generating topological contour boundaries from discrete 2D/3D scalar fields.

Production-grade genpark-ldpc-belief-propagation-decoder-skill skill for AI agents

Production-grade genpark-hamming-7-4-syndrome-decoder-skill skill for AI agents

Production-grade genpark-hdr-histogram-percentile-estimator-skill skill for AI agents

Production-grade genpark-three-phase-commit-non-blocking-skill skill for AI agents

Knaster-Tarski least fixpoint iterative solver computing greatest lower bounds and invariant convergence over complete finite lattices.

Artificial Potential Field (APF) reactive navigation planner for swarm robotics with obstacle repulsion and attractive target tracking.

Information-theoretically hiding and computationally binding Pedersen vector commitments with additive homomorphic properties over prime fields.

Rotated planar surface code syndrome decoder detecting bit-flip (X) and phase-flip (Z) errors using parity-check stabilizer measurements.

Append-only Merkle Mountain Range (MMR) cryptographic accumulator for flyclient proofs, blockchain state commitments, and history verification.