Repo Radar

Graphify converts codebases, documentation, and other files into a queryable knowledge graph, replacing traditional code search.

Ponytail is a prompt engineering technique that makes AI agents generate simpler, more concise code by leveraging existing browser capabilities.

• 80-94% less code
• 3-6× faster
• 42-75% cheaper

Uptime Kuma is an open-source, self-hosted monitoring solution designed to check the uptime of various services. It addresses the problem of needing to rely on third-party services for basic uptime mo

• Monitoring uptime for HTTP(s) / TCP / HTTP(s) Keyword / HTTP(s) Json Query / Websocket / Ping / DNS Record / Push / Steam Game Server / Docker Containers
• Notifications via Telegram, Discord, Gotify, Slack, Pushover, Email (SMTP), and 90+ notification services
• 20-second intervals

MinerU is a document parsing tool designed to convert unstructured documents into LLM-ready formats. It addresses the problem of extracting clean, structured data from various document types for use i

• High accuracy in content extraction and structure preservation

Crawl4AI is a web crawler and scraper that converts web content into LLM-ready Markdown, replacing traditional scraping methods.

• drastically more cost-effective than any of the existing solutions

Headroom is a context compression layer that reduces the token count of inputs before they reach a large language model.

• 60-95% fewer tokens
• 6 algorithms
• reversible

LiteLLM is a Python SDK and proxy server that unifies over 100 LLM APIs into an OpenAI-compatible format.

• 100+ LLMs
• Self-hosted
• Call any LLM in OpenAI format

Codebase-memory-mcp is a code intelligence engine designed for AI coding agents. It solves the problem of slow code analysis by rapidly indexing codebases into a persistent knowledge graph. The system

• Full-indexes an average repository in milliseconds
• the Linux kernel (28M LOC, 75K files) in 3 minutes
• Answers structural queries in under 1ms

AirLLM is a tool that optimizes memory for large language model inference, replacing the need for quantization or distillation.

• 70B large language models to run inference on a single 4GB GPU card without quantization, distillation and pruning
• run 405B Llama3.1 on 8GB vram
• Support CPU inference

Context Mode optimizes AI coding agent context windows by replacing raw tool output with sandboxed summaries.

• 98% reduction in context window size from tool output

LingBot-Map is a feed-forward 3D foundation model designed for streaming 3D scene reconstruction. It addresses the challenge of real-time, continuous scene mapping from live data streams. The system w

• stable inference at ~20 FPS on 518×378 resolution over long sequences exceeding 10,000 frames
• Superior performance on diverse benchmarks compared to both existing streaming and iterative optimization-based approaches

turbovec is a Rust vector index with Python bindings that replaces FAISS for vector search.

• A 10 million document corpus takes 31 GB of RAM as float32. turbovec fits it in 4 GB
• searches it faster than FAISS
• Hand-written NEON (ARM) and AVX-512BW (x86) kernels beat FAISS IndexPQFastScan by 10–19% on ARM

Supertonic is a text-to-speech system designed for local inference with minimal overhead. It solves the problem of relying on cloud APIs for TTS, enabling on-device processing without privacy concerns

• 31-Language Multilingual
• 99M-Parameter Open-Weight Model
• fast enough to turn an entire webpage into audio in under a second

MiMoCode is a terminal-based AI coding assistant that replaces manual coding and command-line tasks.

• terminal-native AI coding assistant
• persistent memory system to keep a deep understanding of your project across sessions
• continuously improving itself

Speech To Speech is a Python package that implements a voice agent pipeline, processing audio through Voice Activity Detection, Speech to Text, a Language Model, and Text to Speech. It solves the prob

• low-latency, fully modular voice-agent pipeline
• runs in production as the conversation backend for thousands of Reachy Mini robots

LongCat-Video is a foundational video generation model, replacing traditional methods for creating video content.

Semble is a code search library for agents, replacing traditional grep+read methods for code retrieval.

• Uses ~98% fewer tokens than grep+read
• Indexing and searching a full codebase end-to-end takes under a second
• ~200x faster indexing and ~10x faster queries than a code-specialized transformer, at 99% of its retrieval quality

GeoLibre is a free and open-source, cloud-native GIS platform designed for visualizing, exploring, and analyzing geospatial data. It addresses the problem of needing a versatile GIS that runs across m

• runs everywhere you do, in the web browser, on the desktop, on mobile, and inside Jupyter notebooks
• keeping your data local and private
• 700+ Free GIS Tools in GeoLibre

This package, SamGeo, simplifies using the Segment Anything Model (SAM) for geospatial data analysis with minimal coding. It processes GeoTIFF files and remote sensing imagery, enabling segmentation w

• simplify the process of leveraging SAM for geospatial data analysis by enabling users to achieve this with minimal coding effort
• Download map tiles from Tile Map Service (TMS) servers and create GeoTIFF files
• Save segmentation results as common vector formats (GeoPackage, Shapefile, GeoJSON)

Eagle is a vision-language model that serves as a backbone for other models, replacing prior VLM backbones.

• LocateAnything now supports batch inference with a pure FlashAttention runtime
• efficient inference on A100, RTX 4090, and other non-Hopper/Blackwell GPUs

This project offers an AST-based semantic code search engine, replacing traditional keyword or regex-based code search.

• Instant token saving by 70%.
• 1 min setup — install and go, zero config needed!