This is a relatively simple project, that allows you to run a script which will use firefox and automatically delete your ChatGPT chats, I made this for myself, but if it helps anyone else, feel fr…

A python program that turns an LLM, running on Ollama, into an automated researcher, which will with a single query determine focus areas to investigate, do websearches and scrape content from vari…

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.

MultiSoul lets you control AI agents running on your own computer from your phone. You can watch messages and tool calls in real time, answer approval questions, and receive task completion notific…

Connect Your Agents And Harnesses With Any Provider 🦚

List of Permanent Free LLM API (API Keys)

AI-powered job search system built on Claude Code. 14 skill modes, Go dashboard, PDF generation, batch processing.

AI job agent: scans 130+ careers pages nightly, scores every role against your resume with an LLM (0–100), alerts you on Telegram, and drafts tailored cover letters + resumes. Free & open source.

A novel framework for Lithium-Ion Battery State of Health (SOH) estimation using Kolmogorov-Arnold Networks (KANs) and physics-informed neural network constraints based on the Verhulst degradation …

The official BatteryLife repository

Local engineering knowledge graph with visual document retrieval (Nemotron ColEmbed), Neo4j GraphRAG, and vision-language answer generation. Processes engineering PDFs into a searchable knowledge b…

OpenKB: Open LLM Knowledge Base

⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA

The agent that grows with you

AI-orchestrated visual production for Obsidian Canvas. Create presentations, flowcharts, mood boards, knowledge graphs, and galleries with intelligent layout and AI-generated content.

Open source personal website builder with 50+ templates, Claude AI customization, and one-click Vercel deployment

tired to lose my ideas on a, why not to put them here?

A library that enables a hallucination-free conversations with code repositories.

Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private.

This project aims to design an AI Agent tool to address the issue of reduced output accuracy caused by hallucinations in LLMs during formal symbolic computations in theoretical physics.

Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns.

📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

心理健康大模型 (LLM x Mental Health), Pre & Post-training & Dataset & Evaluation & Depoly & RAG, with InternLM / Qwen / Baichuan / DeepSeek / Mixtral / LLama / GLM series models

code and data for Jiang, H., Ge, L., Gao, Y., Wang, J., & Song, R. (2023). Large language model for causal decision making. arXiv preprint arXiv:2312.17122.

Vision-first AI agent for desktop automation. Fully offline. Powered by YOLO, OCR & ResNet — building towards local intelligence.