1memvid / memvid
Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.
Ranked by Attention Score: stars gained over the last 7 complete days
34 repositories by Attention Score · Oct 27, 2026 – Nov 2, 2026 (UTC)
Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.
Production-grade Rust-native trading engine with deterministic event-driven architecture
An extremely fast Python package and project manager, written in Rust.
Joy — a local-first personal assistant. Rust core (loop / memory / tools / graph / evals), TypeScript gateways + dashboard, Python thin SDK.
A coding agent for open models like Kimi K3 and GLM 5.3
An extremely fast Python linter and code formatter, written in Rust.
Code-first platform for workflows, apps and AI agents, on the fastest self-hostable orchestrator (benchmarked against Airflow, Prefect and Temporal). Business teams build with AI, engineers control what ships. Open-source alternative to Lovable, Retool and n8n.
Fast, memory-safe camera RAW decoder in Rust: ~40 formats, SIMD, GPU, WebAssembly, ICC colour management. CLI, C, C++, Python and JavaScript bindings.
The fastest PDF library for Python and Rust. Text extraction, image extraction, markdown conversion, PDF creation & editing. 0.8ms mean, 5× faster than industry leaders, 100% pass rate on 3,830 PDFs. MIT/Apache-2.0.
The fast, precise document-intelligence engine for every language: text, tables and metadata from 100+ formats, with OCR, transcription and code intelligence.
Incremental engine for long horizon agents 🌟 Star if you like it!
Extremely fast Query Engine for DataFrames, written in Rust
Visualize, query, and stream to train on multimodal robotics data.
⚡ Automatically decrypt encryptions without knowing the key or cipher, decode encodings, and crack hashes ⚡
A data visualization and analytics component, especially well-suited for large and/or streaming datasets.
A fast type checker and language server for Python
A retro game engine for Python
A vector index built on TurboQuant, written in Rust with Python bindings
NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.
Rust bindings for the Python interpreter
A Rust HTTP server for Python applications
The fastest and the most accurate file search SDK for AI agents, Neovim, Rust, C, Python, Bun and NodeJS
Sampling profiler for Python programs
Effortlessly compose, extend, and observe every service in real-time for the first time ever.
Pinepods is a complete podcast management system that allows you to play, download, and keep track of podcasts you enjoy. All self hosted and enjoyed on your own server!
Apache DataFusion Ballista Distributed Query Engine
Generate Nix packages from URLs with hash prefetching, dependency inference, license detection, and more [maintainer=@figsoda]
Unofficial Dante Controller alternative for iOS/iPadOS, Linux, macOS, Windows, and the web. Discover, route, configure, meter, and monitor Dante audio devices with a native iPhone/iPad app, CLI, browser interface, daemon, and API.
A high performance Python graph library implemented in Rust.
Turn any website into clean, structured data: Markdown, metadata and links from one page or a whole site, in every major language.
TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation.
Python library to parse, analyze and visualize Counter-Strike 2 data
A robust web archive analytics toolkit
Streaming-first technical indicators with a Rust core: native Python, Node.js and WebAssembly bindings plus a C ABI hub for C, C++, C#, Go, Java and R. 514 indicators, O(1) per-tick updates, no system dependencies. Drop-in TA-Lib replacement.