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
69 repos
-
Voice-agent implementations of Rory, the Acme Energy utility billing agent from the VAmoS Energy benchmark
-
A benchmark for evaluating AI agents on realistic business workflows
-
Benchmarks scikit-learn-compatible machine learning libraries
-
Implement one small API on SQLite in any language; we benchmark it on a $12 server (1 vCPU, 2 GB)
-
Autoresearch agents that improve your benchmark: independent re-measurement, enforced budgets, results as pull requests
-
Gym-Anything for Robotics: framework and the RoboWorld benchmark
-
Reproducible navigation benchmarking & residual RL fine-tuning for Wanderland
-
The first exam for code agents in the physical world: frozen robot tasks from many benchmark suites, each answered with a program and verified in a separate sandbox. Runs on Harbor.
-
Evaluation harness for OpenHands V1.
-
Two small, deterministic benchmarks for a first Outerloop run
-
PE Bench: an agent benchmark for private equity deal work (public Voltaic room)
-
An AI agent plays Baldur's Gate 3 on Linux through a Lua mod and an MCP server, seeing only what a player sees. Includes a model benchmark and a playthrough app.
-
A Long-Horizon Benchmark for Self-Improving Inference Systems
-
A Difficulty-Calibrated Benchmark for Building Terminal Agents
-
Easily benchmark a Julia package over its commit history
-
[ICML 2026] A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation
-
Shared correctness gates and validated benchmarks for Campfire implementations
-
Campfire ported to Elixir, with Rails compatibility checks and Rust benchmark comparisons
-
Does injecting biblical Psalms into an LLM's system prompt measurably affect ethical alignment? An empirical experiment using the Hendrycks ETHICS benchmark on Claude Sonnet 4 and GPT-4o.
-
Official code for the SEAR benchmark
-
VirtueBench V2: Multi-dimensional virtue evaluation benchmark for LLMs with tripartite and Ignatian temptation models
-
Campfire in Go, using the standard library and minimal dependencies. Includes compatibility checks and Rust benchmarks.
-
A controllable benchmark for robotic manipulation
-
Lightweight Benchmark Server for Agentic GPU Programming
-
Solver benchmarking tools
-
Kaggle Benchmarks Python library
-
Official repository for "RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies".
-
PokéBench: local and frontier models play Pokémon Red as a benchmark, with a leaderboard and live stream
-
Evidence-driven simulation benchmark for Codex-driven technical physical work
-
BVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in Blender
-
OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
-
JevBench by Benchmark Heaven: benchmark and leaderboard for AI decision models, measuring typed decision accuracy, calibration, latency and cost.
-
Raw results of solver benchmark campaigns run with bodono/solver_benchmarks
-
Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.
-
Physical Analysis: embodied AI benchmarks and aggregate results
-
Open Source AI Accelerator Research Platform Standard / 开源推理研究平台
-
A curated collection of papers, research blogs, open-source tools, benchmarks, and community demos for robot-use agents, including demos powered by GPT-6 Astra. —— Explore our searchable website.
-
Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)
-
OpenMMLab Detection Toolbox and Benchmark
-
AM-Bench: a modular simulation suite and benchmark for aerial manipulation policy learning (CoRL 2026)
-
Offline LLM-judged arena for embedding models
-
Public results and task definitions for FrontierHarness Eval
-
Official Code Repository for the ICLR 2026 Paper "Human Behavior Atlas: Benchmarking Unified Psychological and Social Behavior Understanding" & ICML 2026 Paper "Omnisapiens: A foundation model for social behavior processing via heterogeneity-aware relative policy optimization"
-
CommerceAgentBench: Benchmarking Long-Horizon Agents in High-Fidelity, Stateful, and Reproducible Replicas of Real Online Services
-
An MCP server that lets LLM agents play Civilization VI.
-
A benchmark for evaluating AI agents on realistic business workflows
-
ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits.
-
FrontierSWE is an ultra long-horizon coding agent benchmark that tests implementation, performance eng and ML research
-
Easily benchmark a Julia package over its commit history
-
Same model, different wrapper: a from-scratch benchmark comparing coding-agent harnesses (codex, pi, opencode, cursor, devin) and open models on correctness, speed, and token cost