Your Personal AI Agent on a Short Leash
nanobot is an open-source AI agent engine that runs locally, supports Telegram/Discord integration, MCP tools, and long-term memory without sending data to the cloud.
Language
HomeLanguages
Sections
nanobot is an open-source AI agent engine that runs locally, supports Telegram/Discord integration, MCP tools, and long-term memory without sending data to the cloud.
Apache Ossie aims to solve semantic fragmentation in data stacks by creating a vendor-neutral format for describing metrics once and using them everywhere.
Tired of wrestling with ML model deployment? Triton Inference Server from NVIDIA offers dynamic batching, multi-framework support, and production-ready metrics out of the box.
Prime-RL from Prime Intellect offers a full-fledged environment for training agentic models at scale across thousands of GPUs with async RL pipelines.
Stanford's SNAP group released Biomni, an LLM-based agent for biomedical research that plans CRISPR experiments, analyzes scRNA-seq data, and generates testable hypotheses.
NVIDIA Research's FoundationPose unifies 6D pose estimation and tracking, working out-of-the-box with objects never seen during training. No fine-tuning required.
How to fit AI into smart glasses without going crazy from lag. Meet Needle — a 26M parameter model for instant function calling.
A fork of TradingAgents adapted for Chinese A-shares: seven specialized AI agents debate and analyze stocks before delivering investment recommendations.
Tired of Tuya devices relying on flaky Chinese cloud servers? tuya-local lets Home Assistant control them directly over your local network—no subscriptions, no delays, just instant响应.
Microsoft's TRELLIS.2 generates render-ready 3D assets from a single image in seconds using a 4B parameter model with PBR materials and O-Voxel representation.
Pixelle-Video is an engine for automating short video creation from a single text prompt. It generates MP4s with voiceover, subtitles, music, and AI visuals.
Building multi-agent AI systems doesn't have to be a nightmare. Neuro SAN Studio offers declarative configs and a visual editor to orchestrate LLM agents without endless Python code.
OpenManus is an open-source AI agent that automates browser tasks, data analysis, and more. Built by MetaGPT in just 3 hours as an alternative to the invite-only Manus.
GraphRAG builds knowledge graphs from unstructured data, enabling LLMs to understand connections and answer global questions across massive archives.
I tried Memtrace — a tool that turns your codebase into a knowledge graph for AI agents, indexing 15,000 files in 1.5 seconds without LLM calls.
Discover Y2A-Auto — a Python-based automation tool that handles the entire YouTube-to-Bilibili content pipeline, from downloading and AI subtitle translation to smart metadata generation and publishing.
Discover public-apis, a curated collection of 14,000+ free APIs that has become the go-to resource for developers seeking ready-made solutions for any project.
A Python tool that generates VirtualBox templates and PowerShell scripts to hide VM traces, helping malware analysts and security researchers.
Alexandria transforms any text into a multi-voice audio production using LLM analysis and neural speech synthesis. Here's how it works and whether it's worth trying.
SentrySearch is a CLI tool for semantic video search that lets you find specific moments by typing text queries instead of scrubbing through hours of footage.
Imagine having a personal assistant that works around the clock, searching for free coupons on paid Udemy courses and enrolling you in them.
Discover how Auto_Job_Applier_LinkedIn uses AI to automate job applications on LinkedIn, customizing resumes and cover letters for each position.
ToonComposer uses AI to transform sketches into animated cartoons, handling inbetweening and colorization automatically for animators.
Ever needed to extract data from a PDF or scanned document? Text-extract-api offers an elegant solution combining modern OCR and language models.