Search

Rohinik agent authoring SDK — defineAgent(), typed context, local validation

OE Runtime - Embeddable AI Agent Runtime for Independent Software Vendors (ISVs) and Integrators

Open-source infrastructure for AI agents to collaborate - registry, A2A communication, task pool, payments

Stable, editable PPTX generation for AI agents — semantic IR in, native DrawingML out

Everything the official WeRead (微信读书 / WeChat Reading) Agent Skill does — plus public accounts, RSS/Atom/JSON feeds, book imports, WeRead AI, and write access to your highlights and shelf. One canonical surface of 40 operations through an agent skill, Typ

Phoenix Agent - Autonomous AI system agent for Windows

A full-screen terminal coding agent built with Bun and AI SDK.

Dotted thinking-orb loading animations for AI, agent & voice UIs — ten tuned states plus an amplitude-reactive voice orb, rendered on the UI thread with Skia + Reanimated, for React Native & Expo

Pi Agent hybrid memory extension — HMEM integration for long-term semantic memory, knowledge graph, and reflection engine

Unified Process Reward Model — step-level reasoning quality scoring, 3-tier MC/heuristic/weak-supervision labeling, confidence-weighted MSE training, step segmentation, multi-domain verification, and PRM-guided inference

A lightweight, extensible Node.js CLI agent framework.

Define an AI agent tool once, call it in-process or serve it over MCP.

TDD-native spec framework: tests are the source of truth for verification, ID-bound requirements the source of truth for intent.

A compact terminal coding agent powered by pi and OpenTUI.

TypeScript SDK for browser.ceki.me — rent real browsers of real people

Secure coding agent harness wrappers (Claude Code, Codex, Cursor) with AumOS

Amazon DynamoDB persistence backend for CrewAI Flows with built-in message pruning via agentstate-reducer

Runtime policies for agents — the open-source edge SDK (capture + check + enrichment).

Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and understanding visual and...

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...