Trending

CLI and GitHub Action that scans repos, logs, and CI artifacts for leaked LLM reasoning-trace blocks from Anthropic, OpenAI, and Google.

An open-source benchmark for testing whether LLMs can follow long arithmetic derivations without using tools. It compares models on recall-proof inputs, logs digit accuracy, and reports results across multiple endpoints and model families.

A Python computer vision tool that analyzes gameplay videos, detects key events, clips highlights, and generates session reports and montages.

Open-source self-improving QA agent for web and mobile testing. It lets teams write natural-language E2E tests, stores execution memory, and supports self-healing runs across web, Android, and iOS.

A live demo and write-up showing a 3.16M-parameter INT4 transformer running entirely in on-chip memory on a Xilinx Kria KV260 FPGA, with measured token rates and hardware details.

AI shopping agent that reviews product links for price manipulation, review authenticity, and seller reputation, then returns a Tick, Clip, or Skip verdict.

FAAAH is a dependency-free, OpenAI-compatible local proxy that routes requests through text files and AI coding agents. It is aimed at developers who want to reuse an existing agent subscription as a backend for tools that expect the OpenAI API.

A browser-based computer vision project that detects cursor hotspots in screen recordings using temporal motion cues, ONNX Runtime Web, and WebGPU. The repo includes a live demo, training scripts, synthetic data generation, and baseline comparisons against YOLO models.

GreatArrow.ai is an open beta workspace that gives Claude, ChatGPT, Cursor, Gemini, and other MCP-compatible clients shared memory plus action access across tools like Gmail, Slack, GitHub, Notion, and Jira.

Bb is an agentic IDE that can control itself, with a desktop app, CLI, web app, and HTTP API for orchestrating coding agents and running work in live threads.

Kotro is a local control plane for coding agents that governs MCP tool actions and LLM traffic with one binary. The page shows install options, supported clients, dashboard access, and concrete controls like schema pinning, redaction, cache, budget, and circuit breaker behavior.

Compass is a local-first code knowledge graph engine in Rust that turns codebases and project artifacts into searchable, queryable graphs. The page shows support for architecture mapping, change-impact analysis, historical graph diffs, deterministic CompassQL queries, and integrations like VS Code, MCP, and export form

Macro is an open-source team workspace that combines email, chat, docs, tasks, agents, calls, and CRM in one linked system with shared AI memory.

Research preview for a voice-agent reasoning harness that lets a realtime assistant think between turns without adding in-band latency. The page includes benchmark results, pricing, example behavior, and a description of the architecture behind Waterr’s AI meetings.

An open-source app that takes a finger-frame gesture video and turns the framed area into an AI-generated scene, then composites it back into the original clip. It includes a browser demo, local run instructions, and Python CLI scripts for offline use.

Local-first private planning and decision workspace that turns messy documents into structured plans, grounded outputs, and traceable decisions with citations and audit trails.

An open-source agent-driven package manager for versioned, checksummed, approval-gated tasks run through Claude Code, Codex, Gemini CLI, OpenCode, or Antigravity.

OpenEdit is an open-source, agent-driven video editing pipeline that lets coding agents add subtitles, cut, reframe, and generate motion graphics without a GUI or timeline.

Open-source runtime guardrails for AI agents that intercept unsafe tool calls before they execute, aiming to block prompt-injection-driven exfiltration and other policy violations.

Bourdon is a recognition-first memory runtime for AI agents, built to share memory across tools like Claude Code, Codex, Cursor, and others. The site shows install commands, product positioning, pricing, and several live field tests.

A 1.26B academic tutor model from Zyora Labs, built from scratch and tuned for concept-first explanations in English, Tamil, and Hindi.

A web tool that compares how many AI tasks different models can buy per hour of work across countries, using wage and benchmark-cost data.

A Claude Code plugin and Chrome extension for capturing a website and rebuilding it pixel-by-pixel with automated diff checks.

Symbio is a local AI assistant that learns from user corrections, builds training data from notes, and can fine-tune itself over time. It supports file operations, sandboxed shell commands, RAG, a Telegram bot, and a demo with MoA and skill adapters.