Newly Accepted

An open-source research framework for structured LLM evaluation, claim verification, and source-grounded reflective reasoning. The repo describes modular components for retrieval, semantic scoring, skeptical claim checking, and benchmark-style epistemic assessment.

GitGalaxy is a Python-based static analysis and knowledge graph engine for deep repository intelligence. It maps codebases at the function level, supports 50+ languages, runs locally, and exports JSON and SQLite for querying and AI-agent workflows.

Harness is an open-source app for running a team of AI agents, with support for Claude, browser control, mobile access, and a headless server mode for remote use.

DAC is a dashboard-as-code CLI and framework for building interactive dashboards from YAML and TSX, with a built-in semantic layer and an AI agent workflow for updating dashboards.

A local tool that estimates GitHub Copilot AI-credit costs from usage data and generates an HTML report. It pulls from VS Code, OpenCode, Pi, Copilot CLI, and Copilot for Xcode, with CLI options for date ranges, model mapping, and JSON output.

Chrome extension that uses Gemini Nano via Chrome’s Prompt API to rewrite comments and posts live in a chosen tone, fully on-device with no API keys or backend.

A Claude Code playbook for engineers who want to drive internal adoption on their team, with guidance on what to share, how to answer questions, and a 30-day rollout plan.

A public slide deck about vLLM-compile, a project focused on bringing compiler optimizations to LLM inference and speeding up torch.compile for vLLM workflows.

A research article from Applied Compute on how agentic, tool-using workloads differ from traditional LLM benchmarks, with production observations, workload profiles, and an open-source harness for replaying traces.

Rinhelp is an AI support diagnosis tool for technical support teams. It starts from Crisp support threads, pulls evidence from GitHub and Sentry, and returns a reviewable diagnosis draft for internal use.

pi-hosts is a tool for the Pi coding agent that adds named SSH targets, cached host facts, guarded remote command execution, and JSONL audit logs for server work.

SPARKIT is a scientific research agent delivered through an API. It searches literature, reads PDFs, runs analyses, and returns cited Markdown reports for research workflows.

Gate is an agentic desktop OS for developers that runs AI desks locally, extracts reusable skills from completed work, and logs every action with receipts. The page shows install flow, platform limits, model requirements, sandboxing, and a clear comparison with Cursor/Aider.

Chrome extension for exporting Claude chats to PDF, Word, Google Docs, or Notion, with options to export selected messages or full conversations and customize font, size, and text color.

Ragnerock is a research intelligence platform that turns raw sources into queryable, structured data. It supports extraction, analysis, and research workflows across SQL, Excel, PDF, HTML, images, and other sources, with audit trails and deployment into existing infrastructure.

Open Bias is an open-source reliability harness for LLM apps and agents that enforces rules at runtime. It sits between your app and an LLM provider, using RULES.md policies to trace, block, or fix off-policy behavior.

A React mini-arcade component for turning loading screens into playable one-button games while long tasks run. It includes multiple game modes, skins, score tracking, achievements, and simple props for embedding in apps.

A native macOS app that uses Claude to act as an autonomous coding agent for Apple platform development. It can inspect an Xcode project, make edits, build, launch, and validate changes with xcodebuildmcp and UI automation.

Open-source infrastructure for computer-use agents, with sandboxes, SDKs, benchmarks, and desktop automation tooling for macOS, Linux, Windows, and Android. The repo also includes Cua Driver, CuaBot, Cua-Bench, and Lume for VM management.

Open-source voice AI from Microsoft with both long-form text-to-speech and speech recognition models. The repo highlights 90-minute multi-speaker TTS, 60-minute single-pass ASR, multilingual support, hotwording, and links to docs, Hugging Face, playground, finetuning, and papers.

An interactive dashboard that analyzes New York Times coverage since 2000 using the NYT Archive API, with views for reporters, beats, sections, subjects, geography, obituaries, and corrections.

Lightport is a lightweight AI gateway that makes LLM providers OpenAI-compatible. The repo shows supported endpoints, a long provider list, quickstart commands, request examples, and active maintenance signals.

Claude Code plugin that blocks dependency edits until a fresh, source-cited version check is recorded, helping prevent hallucinated or stale package versions across npm, pip, Poetry/uv, Cargo, and NuGet.

Archik is a developer tool for describing architecture diagrams in plain YAML and rendering them as a live canvas or SVG. It integrates with Claude Code through an installed skill and slash commands, and adds validation, traceability, and CI-friendly rendering.