AI Infra agents

Run a free 35B multimodal LLM on Kaggle GPU — accessible from any OpenAI-compatible client

Personal AI assistant with cognitive memory, tier-aware tools, and 20+ messaging channels

An interactive educational platform for understanding AI agents

Hermes Herald — dispatch tasks across Hermes profiles with fail-closed model routing, SSE auto-delivery, approval relay, and per-call subagent model selection.

MoziAI-35B: Local open-source financial AI LLM. 35B MoE model compressed to 15.5GB via MoziSmartBit quantization. 256K context, vision, tool calling, 140+ tok/s on consumer GPU. Based on Qwen3.6-35B-A3B.

Role-playing autonomous agent orchestrator managing crews (CrewAI style)

Real-time neural 3D asset generator and PBR texture synthesizer (Luma Genie style)

Pan-African and global cross-border payment gateway with mobile money rails (Flutterwave style)

Resilient agentic document parser & schema drift workflow automaton (Gumloop style)

Institutional DCF/LBO financial model and 10-K audit builder (Rogo style)

Stateful OS-tier memory virtualization agent with auto-paging (Letta / MemGPT style)

Conversational language tutor and pronunciation fluency coach (Speak style)

Vertical beauty e-commerce omnichannel recommendation engine (Konvy style)

Secure agent automation with full audit trail, human approval gates and compliance-grade orchestration (Tines 3B style)

Field guide and local-first tools for token and context optimization in LLM agents.

UGC creator brief programmatic auction & video matchmaking (Cohley)

The incremental build system for AI applications.

Observability infrastructure for self-improving agents: every run written into the repository as plain files the agent can read

Cryptographic receipts that prove an AI output was not altered. Offline verification in 21 lines, no server or account. Ed25519 + SHA-256, 128-byte Rust core, optional ML-DSA-65 post-quantum signatures. Python and Rust.

Academic workspace for university students: Drive-synced notes vault, grounded AI, planner, GPA, SRS flashcards, and a PWA.

Agentic dev workspace & live telemetry feedback loop (Xirp style)

Agent-native AI support that turns your docs into answers for your community. Built for your agents with skills and MCP.

Always-on AI agent with persistent long-term memory, sleep-time consolidation, and dreams — runs 24/7 on a small local LLM (Ollama, 2B params, zero dependencies)

CrestApps.Core is the AI application framework for .NET. It gives you the orchestration, management, chat, document, RAG, MCP, A2A, agent, reporting, and extensibility building blocks needed to add production-ready AI to an existing application without stitching together a pile of disconnected SDK samples.

Lightweight graph engine for AI graph context, memory, and agent harness with Rust Core.

DBOS durable execution for the Vercel AI SDK

Co-Dialectic: catch your AI agreeing with you to please you, not because you're right. Sycophancy detection, cross-family judging, and prompt coaching that runs during the conversation rather than auditing after. Free and open source. Works with Claude, ChatGPT, Gemini.

RAG pipeline with embeddings + semantic retrieval

把小爱音箱接入任意 OpenAI 兼容大模型：多音箱隔离、网页管理、语音切模型、保存即生效、多架构 Docker 镜像

Hands-on LangChain learning repository covering Chat Models, Prompt Templates, Chains, RAG, Agents, and Tools with practical Python examples.

NyatBot — a Telegram group-chat agent on the path from chatLLM to AGI

⚡ Rotom — 自动化 CTF 答题 Agent:黑板协同 · 广度优先调度 · 全程审计。像洛托姆一样,潜入哪类题,就长成解决它的形状

Official module library for the start CLI

Ship AI products powered by the best harnesses without building another agent loop

Learn harness orchestration: seven notebooks that climb from one agent call to a system that writes its own execution graph. Companion to the AlphaSignal talk.

Long-term memory for AI assistants, local. Rust + Qdrant + ONNX, served over MCP. Hybrid search with reranking.

Retrieval-Augmented Generation (RAG) Explained, covering its working principles, components, benefits, applications, challenges, and future prospects.

High-performance semantic router for AI systems with uncertainty-aware routing, model selection, and cognitive depth control.

LangGraph multi-agent pipeline for BEC fraud detection — Reply Mirror Hackathon April 2026 (Malto-Team-3)

LLM personal assistant

RAG (Retrieval Augmented Generation) on Android

Neuron AI PHP Framework documentation

Predefined skills for the freeact agent library

A console application demonstrating how to create a copilot using Semantic Kernel and its various features

Marketing frameworks optimized for OpenClaw. Leaner context, faster execution.

ARCHIVED (read-only). Canonical source moved to github.com/mapleleaflatte03/meridian

Computer Use for Agentic Process Automation

Foundation for the Haive AI agent framework — engines, graph builder, state schemas, persistence, and stores

🤖 GAI is a flexible Go framework for building agent-style applications on top of LLMs

Effect-first browser automation for Cloudflare Workers. Give it a prompt, get a completed task.

Open BTC 5-minute prediction market sandbox for AI agents — register with one API call, get 1,000 test credits, and place a live order

Local-first, AI-native LinkedIn messenger CLI. Sync your inbox to plain JSONL files in a git repo, pipe to agents, send from the command line.

The Requesty integration package for the Vercel AI SDK.

Detect AI agent runtimes so CLIs can choose agent-friendly output

AI-powered CV and Cover Letter Generator using CrewAI

Production-ready agent implementations: SimpleAgent, ReactAgent, MultiAgent, MemoryAgent, RAG variants, and more

로컬 LLM을 이용한 로컬 AI 커뮤니티 웹보드 서버입니다.

Persistent memory for AI agents. Single Rust CLI, hybrid Gemini + FTS5 + RRF retrieval. R@5 = 0.99 on LongMemEval S (beats MemPalace). Agent-native: no MCP, no server, just shell out.

A multi-agent workflow that resolve tasks using powershell

The easiest way to supercharge your apps with LLM!

A simple Chainlit app for generative question-answering with LangChain and OpenAI.

Using GPT-3 to query AEAT documentation about Renta 2022

A Graph RAG implementation using Neo4j and LangChain

combines web search, Retrieval-Augmented Generation (RAG), reflection, summarization, and follow-up question generation to provide comprehensive answers to user queries

This repository provides the building blocks for integrating LangChain, LangGraph, and the Tilores entity resolution system.

This experiment will verify different use cases of LLM using LangChain, which include chat, role-playing, and document-based QA.

Proof of Concept Implementation of Langchain in Haskell

The zero-boilerplate LLM framework for humans.

RAG Evaluation Pipeline with RAGAS

A lightweight framework for building LLM applications, with similar interface as LangChain, but more concise internal implementation.

This project offers hands-on examples for LangChain and LangGraph, complementing their textbooks with practical guides on workflows, tools, and agentic RAG techniques.

An advanced AI chatbot implementation that combines the power of Groq's LLM with LangChain's tools for internet access, web searching, and conversation memory. This chatbot can search the internet, access Wikipedia, and maintain conversation context while providing informative responses.

It shows how to use langchain for sagemaker endpoint.

Flan-t5 model fine tune LoRA and Langchain

An Agentic RAG implementation using Langchain and a telegram client to send/receive messages from the chatbot

LangChain Utilities for prompt generation from documents, URLs, and arbitrary files - streamlining your interactive workflow with LLMs!

A CUI-based simple werewolf game with `autogen`

Notebooks for the Built Multi-Agent Applications with AutoGen Course

Bu depo; Microsoft AutoGen ile yaptığım/deneysel çalışmalar, entegrasyon denemeleri ve çoklu LLM sağlayıcı karşılaştırmalı örneklerini içeren bir çalışma alanıdır.

Framework-agnostic AI agent library for building single and multi-agent systems

This module implements a post-training mechanism that allows a language model to explore various reasoning branches (chain-of-thoughts) using a Monte Carlo Tree Search (MCTS) framework. It selects the branch with the best answer using a cosine similarity evaluator that compares the candidate answer to a known correct answer.

Atlaso — desktop app + Python SDK for confidence-flagging AI agent memory. Apache-2.0.

A template repo for development with the AEA framework

AniBaba is an AI-powered anime recommendation system that provides personalized suggestions based on natural language queries. Leveraging Retrieval-Augmented Generation (RAG), it understands user preferences and retrieves relevant anime from a semantic knowledge base to offer a conversational and discovery-rich experience.

Teach your LLM to dynamically call your services in Kubernetes

Context Engineering - The art of providing all the context for the task to be plausibly solvable by the LLM.

JavaScript for MultiMindSDK – bring advanced context transfer and multi-LLM orchestration, Node.js apps, and web tools

Foundational bootcamp on LLM usage (prompting & inference) → tooling & orchestration (LangChain, agents) → Retrieval-Augmented Generation (RAG) → advanced multi-tool/agent patterns.

Agentic TRACE is the implementation of the framework described in: https://appliedingenuity.substack.com/p/the-verifiable-orchestrator-a-new

A Kotlin Spring AI demo uses the Agentic approach to demonstrate "Let LLM think on graph schema"

A high-performance Rust AI agent runtime inspired by the Agno framework.

A python CLI tool that bootstraps production-ready GEN AI project structures with best practices and modular organization out-of-the-box

Simple and blazingly fast dynamic evaluation platform for benchmarking Large Language Models

AI assistant that answers questions from your documentation

Personal User-Centric Immutable OS Based on NixOS and Pi.Dev AI Agent, where the agent is a first class citizen of the OS, and also dictates the UX experience

🤖 The simplest way to build Telegram Bot in the whole multiverse

A suite of tools for building virtual assistants and chatbots - by ANS Group

Create a chatbot in less than 2 minutes with MLX Server, Chainlit and Llama3

Multi-modal Chatbot based on OpenAI

A LLM powered Telegram chatbot.