New AI agents this week

by zai-org

Z.ai's coding agent harness. Powerful, intelligent, extensible.

by awlevin

Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.

by AbdelStark

A curated list of official resources and community projects for TypeSafe, System One models, and Jev.

by ethanplusai

Astra plans and reviews; DeepSeek Flash builds. A native Codex workflow with phased tasks, verification, safe installation and reversible setup.

by cobanov

A curated, source-backed list of projects built with Jev, TypeSafe AI's System One model for typed decisions.

by logicrw

Awesome Jev: source-backed open-source ecosystem radar, plain-language project discovery, and automatic GitHub sync

by Qiuner

An explorable island world to learn AI coding and build real projects with AI agents. Powered by DeepSeek Harness.

by ruc-datalab

EvoOntology: A Self-Evolving Ontology Layer for Data Agents ⚙️ EvoOntology插件为Claude Code/Codex 建立&进化本体层

by Heman10x-NGU

Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE)

by kitze

Self-hosted, versioned skills library for AI agents. MCP, scoped clients, and optional Jev recommendations.

by Oldcircle

An agent skill that finds where a photo was taken — OpenStreetMap geometry, elevation skylines, satellite imagery and street view — and shows its work. Works with Claude Code, Codex, Cursor, Gemini CLI, OpenCode and GitHub Copilot.

by NiazMorshed2007

Local-first MCP plugin for continuous software-quality review by AI coding agents, powered by Jev.

by Matthew0822

Audit AI agent tool-call transcripts: hash-chain sealing, deterministic replay, and scope overreach checks. Dependency-free Python CLI.

by itsmostafa

mcp connector to give your AI agent direct access to typesafe ai's jev model

by indada

Verification-driven AI software iteration, powered by the OpenAI Codex SDK. Self-hosted agents turn goals, GitHub Issues and PR feedback into tested, reviewable changes, with bounded execution and human control over merging and deployment.

by valentynkit

Typed decisions with TypeSafe's Jev, the first System One model

by JourniOne-ai

JourniOne 旅行规划 Skill：从灵感与逐日路线，到带地图、可分享的 Travel Journal，按需衔接酒店与航班。

by agentscope-ai-java

Build distributed, production-grade, long-running agents.

by Dicklesworthstone

Rust CLI powered by Jev from TypeSafe.ai that ranks agent skills for the next step using live session context. Includes Claude Code hooks, structured JSON, abstention, and local feedback. Requires a TypeSafe API key.

by haplollc

Dotted, honestly-3D loading indicators for AI and agent interfaces in SwiftUI. Nine hand-tuned designs, two tuned sizes.

by RectangleStory

⚡ Modular prompt-engineering framework for AI Agents (Cursor, Claude Code, Copilot). Forces structured SDLC, linear execution, context isolation, and systematic debugging via a standalone Windows launcher. Stop vibe coding, start agentic discipline! 🚀

by RomanSlack

Camera-only autonomous drone in MuJoCo with a small judgment model (TypeSafe Jev) in the loop at 2.5Hz

by savka777

Say it, and your Mac does it. A computer-use harness on Jev that reads the screen through Accessibility. Fast, no vision model

by kraayenjon

A curated list of Jev use cases, projects, SDKs, and resources. Jev is TypeSafe AI's System One model for fast, typed decisions in software — Choice, Score, and Noul with calibrated probabilities.

by kishormorol

An Agent Skill that turns the asks you keep typing into short commands, mined from your own Claude Code and Codex history. Works in Claude Code, Codex and Cursor.

by QiantangCredit

An autonomous AI agent framework for authorized CTF and security labs

by mutonby

Desktop multicam recorder for macOS: records your screen and webcam in sync, then Claude Code or Codex edits the final video — shot selection, subtitles, graphics and SFX.

by mitkox

Self-hosted engineering software factory: Temporal, CubeSandbox agents, deterministic verification and durable evidence. MIT-licensed Machinist fork.

by jamiepinheiro

Allow an AI agent to control an iPad through a USB input tool, native screen sharing, and a control server.

by makifbaysal

Local-first agent platform: board + role agents + Claude Code runs, all on your own Mac

by aibuildai-inc

AIBuildAI LLM-Post-Train Agent: a recursive self-improving (RSI) agent for autonomous LLM post-training

by August06exe

让完全不懂技术的人拥有一台真正每天在干活的专属 AI agent ｜ Open-source consulting playbook: ship self-hosted AI agents that non-technical users actually use

by Guo-Yixin

CODING — a local-first AI coding agent for repository-aware planning, execution, validation, and delivery.

by Mayuqi-crypto

⚡ Ultra-fast, index-powered local file search skill for AI agents (Cursor, Codex, PI-Desktop) using Voidtools Everything

by lxsssssss

by ccai40359-wq

Multi-agent workflow skills for mainstream coding agents (Claude Code / Codex / Cursor): evidence-governed research fan-out, dual-channel document reading, dev delivery with independent review and visual acceptance.

by GPUtw-ai

GPUtw.ai official AI knowledge package — teach Claude Code, Codex CLI, Cursor, Copilot and Gemini CLI to use the GPUtw GPU cloud REST API

by penso

Native macOS client for Herdr, built with Rust and GPUI. View terminal sessions, workspaces, Git worktrees, and agent activity through your local Herdr daemon.

by Devin-AXIS

Jev DSH 决策引擎｜面向 Agent Harness 的结构化决策插件。原生支持 DeepSeek Harness，通过 iPolloWork 支持 OpenCode、Codex Harness。

by friday-memory

⚡ The open-source persistent cognitive memory layer for AI coding agents. Stop your Cursor, Claude & Copilot from having amnesia.