New in Agents
The agents projects, models and papers gaining momentum, newest and fastest first. Updated every two hours.
| Signal | Peak day | Total |
|---|---|---|
| Repo · morluto/reaREA lets AI agents reverse-engineer any software, no source neededREA is a TypeScript toolkit that lets you attach an LLM agent to tools like Ghidra, Hopper or static JavaScript analyzers, so the agent can inspect binaries, Electron apps, .NET assemblies or websites and explain how they work. It runs locally, shows the evidence behind each conclusion, and can even generate a re-implementation of the feature you examined. | ▲ 15.2k | 369k |
| Repo · storytold/photocraftNew · 23d oldRust-powered Photoshop clone rakes in 3k stars overnightPhotoCraft is an open-source image editor that replicates Photoshop’s layers, masks, adjustment layers and PSD compatibility. It runs natively with GPU acceleration via wgpu, so edits stay offline and fast. | ▲ 3.1k | 71.5k |
| Repo · cloudflare/security-audit-skillCloudflare's security-audit skill automates multi-phase code auditsThe repo provides a coding-agent skill that runs a six-step, machine-readable security audit, from reconnaissance to independent verification and neutral reporting. It orchestrates isolated agents to hunt for bugs, validate findings, and output JSON and markdown reports. | ▲ 3k | 40.3k |
| Repo · DietrichGebert/ponytailPonytail AI plugin slashes code size by half for devsPonytail lets an AI agent rewrite requested code into the fewest necessary lines, reusing existing components instead of generating fresh code. In tests it cut code volume by 53%, reduced development time by 41% and lowered token usage. | ▲ 1.9k | 174k |
| Repo · debpalash/VoiceStudioOpen-source ElevenLabs clone lets you dub, clone, and transcribe locallyVoiceStudio runs on your computer and can copy any voice, generate speech in 646 languages, dub videos, transcribe audio and create audiobooks. It ships as a desktop app with a one-line installer and works without sending data to the cloud. | ▲ 1.9k | 82.1k |
| Repo · stablyai/orcastablyai/orca | ▲ 1.7k | 103k |
| Repo · Graphify-Labs/graphifyGraphify-Labs/graphify | ▲ 1.4k | 133k |
| Repo · google-research/harness2New · 17d oldgoogle-research/harness2 | ▲ 1.1k | 18.2k |
| Repo · Niko1221/StrataNew · 29d oldNiko1221/Strata | ▲ 1.1k | 30.8k |
| Paper · Deep Search in Real-World Web EnvironmentsNew Benchmark Tests Deep Search Agents on Real-World WebThe paper introduces a benchmark that evaluates how AI agents perform end-to-end research across the live internet, handling diverse sources, media types, and constantly changing content. It measures an agent’s ability to locate, retrieve, and synthesize information beyond static retrieval datasets. | 109 | |
| Lab · Turning Database Grading into RL Rewards: Post-Training Agents with ThinkingBoxTurning Database Grading into RL Rewards: Post-Training Agents with ThinkingBox | ||
| Lab · Stream low-latency speech from AI agents using Kokoro TTS on Amazon SageMaker AIStream low-latency speech from AI agents using Kokoro TTS on Amazon SageMaker AI | ||
| Paper · Heartbeat Thinking: Speculative Reasoning and Tool Execution While Listening in Realtime Voice AgentsHeartbeat Thinking: Speculative Reasoning and Tool Execution While Listening in Realtime Voice Agents | 16 | |
| Hacker News · Patch the Planet: global response coordination as agents uncover vulnerabilitiesPatch the Planet: global response coordination as agents uncover vulnerabilities | 265 | |
| Paper · Toward Recursive Self-Improvement in Physical AIToward Recursive Self-Improvement in Physical AI | 23 |