Dev
GitHub repos gaining traction - what high-signal users are starring and what's climbing the board, captured daily and enriched from GitHub. Raw material for spotting new tech and patterns worth building on.
3,195
repos tracked
105
surfaced this week
193
created < 30d
Python
top language
63 repos
-
Website of the Computational Linguistics & Psycholinguistics unit, Tilburg University
-
Python package for WikiMedia dump processing (Wiktionary, Wikipedia etc). Wikitext parsing, template expansion, Lua module execution. For data extraction, bulk syntax checking, error detection, and offline formatting.
-
Wake and Break: a PSP exploit for AMD navi31 (RX 7900) that makes the card accept unsigned IP firmware. Not persistent: a cold power cycle restores stock.
-
Ephemeral Workspaces, durable shared history. LayerFS gives every agent a complete, writable filesystem Workspace over shared committed history, without copying the base. Agents work in parallel, commit what changed as deduplicated checkpoints, then branch, rewind or merge. Try it with LayerFS × DSH.
-
Tools for managing BibTeX bibliographies: automatically update preprints to published versions and filter to only cited references.
-
An open-source document parsing model with SOTA accuracy and speed, using an RSI loop during post-training.
-
A Long-Horizon Benchmark for Self-Improving Inference Systems
-
Full-text reference readings in markdown, converted from PDFs and web articles. Designed so that agents and humans working on AI cognition, phenomenology, and collaborative research can read the same source material directly — no PDF parsing, no web scraping, no access barriers.
-
A shared, persistent world for people and AIs — the networking, persistence, and multi-participant layer over the eidoverse-video toolkit. Two planes: an append-only world log + lossy presence.
-
★ 47 castorini/onboardingOnboarding guide to Jimmy Lin's research group at the University of Waterloo
-
Phi-Bench (Φ-Bench): 85 open-source LLM-infrastructure engineering tasks for frontier LLMs & coding agents (KFC/LH/E2E). Self-contained public Dockerfile + offline scoring + reference solution per task. Website: llminfrabench.com
-
OpenClaw context engine plugin that integrates ByteRover CLI for persistent, queryable conversation memory.
-
WHATWG-compliant HTML parsing, mutation, and serialization for Python, powered by Rust's html5ever
-
Proceedings of 2nd Workshop on Diversity in Artificial Intelligence
-
PMLR Processing Scripts
-
A library that provides an embeddable, persistent key-value store for fast storage optimized for AWS
-
University of Waterloo CS PhDs
-
Fast, versioned weight updates for LLM serving and training
-
A video editor that rewrites itself. Ask, and it writes the next version of itself, in place, undoably.
-
Redesign mockup of the Bar-Ilan University CS & AI department website
-
Raw data files and conversion scripts for CLDF output for Jambu data.
-
XHTML to docx conversion
-
OpenBLAS is an optimized BLAS library based on GotoBLAS2 1.13 BSD version.
-
GPU-optimized version of the MuJoCo physics simulator, designed for NVIDIA hardware.
-
An open source agent microharness featuring persistent agency and recursive LLMs. Of bash, by bash, for bash; it's shells all the way down.
-
Playing Prince of Persia (1989) using Reinforcement Learning.
-
Portable Harmony conversation rendering and parsing
-
Bash interpreter written in pure Elixir. Execute shell scripts from Elixir with compile-time validation, persistent sessions, and the ability to extend Bash with Elixir functions.
-
Refactored version of NetHack built for binding to PufferLib
-
📢 Production-ready python event bus library with support for async and sync handlers, forwarding betwen busses w/ parent event tracking + loop prevention, FIFO and concurrency options, and WAL persistence. Powers the browser-use library.
-
Exo is an agent + harness architecture that is fully recursive, able to safely edit all aspects of itself at runtime to get better at your tasks.
-
Open-source graph-based presentations from versioned JSON. Select and present in the browser, validate with the local CLI, and export offline.
-
A persistent, real Jupyter kernel for agents.
-
the extensible, customizable, self-documenting, real-time multi-agent computing environment
-
Local code intelligence for developers and AI agents. Connect code, docs and infrastructure in a persistent graph, with CBM Lens, MCP tools, agent integrations and change-aware test selection.
-
Hierarchical agent loops with recursive self-organization.
-
A breadth-first version of the UNIX find command
-
XHTML to docx conversion
-
Code for the papers: “Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling” and “Adaptive Block-Scaled Data Types”
-
Set up your GitHub Actions workflow with a specific version of https://docs.astral.sh/uv/
-
🔍 ugrep 7.8 file pattern searcher -- a user-friendly, faster, more capable grep replacement. Includes a TUI, Google-like Boolean search with AND/OR/NOT, fuzzy search, hexdumps, searches (nested) archives (zip, 7z, tar, pax, cpio), compressed files (gz, Z, bz2, lzma, xz, lz4, zstd, brotli), pdfs, docs, and more
-
Python-first native robotics simulation and reinforcement-learning environments
-
PyTorch native quantization for training and inference
-
PubGrub version solving algorithm implemented in Rust
-
Persists tmux environment across system restarts.
-
Build immersive AR and interactive 3D. Free and open.