New
Everything new in AI as it appears: launches announced by the labs, brand-new models, datasets, papers and open-source tools. Checked every minute or two. Launches feed · Trending · News
Live now
- Connecting…
Yesterday
- Tool@agentproto/adapter-claude-code
@agentproto/adapter-claude-code — AIP-45 AGENT-CLI adapter for Anthropic's Claude Code via @agentclientprotocol/claude-agent-acp. Spawns the ACP wrapper and drives Claude
- Tool@agentproto/llm-endpoint
@agentproto/llm-endpoint — a multi-surface LLM proxy gateway. Exposes Anthropic Messages, OpenAI Chat Completions, and OpenAI Responses API surfaces with transparent prov
- Toolwhalibmob
Node.js library for WhatsApp — register a number over SMS, or link as a companion by QR. Signal E2E encryption, media, groups, channels.
- Toolnexus-ai-pro
Typed AI framework for TypeScript: provider routing and failover, durable agent graphs and workflows, retrieval over any vector store, MCP, evals, guardrails, and cost co
- Tool@eoasmxd/freya
Freya - Lightweight Microkernel AI Agent System | 轻量级微内核智能体系统
- Tool@sema-agent/core
Stateless, task-oriented AI agent core
- Tool@suveren/gateway
Suveren gateway — local agent gateway built in compliance with the Human Agency Protocol (HAP). Runs the UI, control plane, and MCP server in one Node process.
- Toolrust-store-node-darwin-arm64
Node.js binding (napi-rs) for the rust-store multi-backend data engine: GQL parsing, permissions, computed columns and SQL dialect translation for MongoDB, MySQL, SQLite
- Toolrust-store-node
Node.js binding (napi-rs) for the rust-store multi-backend data engine: GQL parsing, permissions, computed columns and SQL dialect translation for MongoDB, MySQL, SQLite
- Toolrust-store-node-linux-arm64-gnu
Node.js binding (napi-rs) for the rust-store multi-backend data engine: GQL parsing, permissions, computed columns and SQL dialect translation for MongoDB, MySQL, SQLite
- Toolrust-store-node-linux-x64-gnu
Node.js binding (napi-rs) for the rust-store multi-backend data engine: GQL parsing, permissions, computed columns and SQL dialect translation for MongoDB, MySQL, SQLite
- Toolrust-store-node-win32-x64-msvc
Node.js binding (napi-rs) for the rust-store multi-backend data engine: GQL parsing, permissions, computed columns and SQL dialect translation for MongoDB, MySQL, SQLite
- Toolnodejs-store
Multi-backend data layer for Node.js (MongoDB, MySQL, SQLite, PostgreSQL, local disk): pure JSON schemas, GQL tree queries compiled to a single native query, GROUP BY/HAV
- Tool@apify/actors-mcp-server
Apify MCP Server
- Toolsphica
Records Claude Code and Codex sessions on your machine and keeps past implementation and decisions, with their sources, for your agent to find.
- Toolopencode-rag-plugin
OpenCode plugin for local-first RAG-based semantic code search
- Toolmaster-skill
FoJin-powered Buddhist AI persona framework — source-grounded, boundary-aware, fidelity-tested, runtime-ready. 16 pre-built masters across 印度 / 汉传 / 藏传 / 南传, plus four te
- Toollangchain_agentx_stream_ui
React session timeline component library for LangchainAgentEvent SSE streams
- Toolwindows-local-ai-one-click-runtime
Windows utility focused on one-click local AI setup, local AI runtime, and Windows AI setup for local AI workflows.
- Toolollama-windows-model-library-manager
Windows utility focused on ollama model manager, model library, and download local models for local AI workflows.
- Toolwindows-cuda-local-ai-setup-helper
Windows utility focused on cuda setup, nvidia local AI, and cuda environment for local AI workflows.
- Toollocal-ai-vram-oom-recovery-helper
Windows utility focused on out of memory recovery, vram error, and local AI crash for local AI workflows.
- Toollocal-ai-model-download-queue-manager
Windows utility focused on model download manager, resumable downloads, and local model queue for local AI workflows.
- Toollocal-ai-model-cache-storage-cleaner
Windows utility focused on model storage cleanup, unused local models, and AI cache cleanup for local AI workflows.
- Tool@brutalsystems/muster
Launch instructed, reachable local agent sessions
- Tool@akagilnc/pi-workflow-roles
Soul-bound workflow roles for Pi
- Tool@falkenslab/agent-kit
Library for building an agent on top of the Claude Agent SDK
- Tool@cortexkit/opencode-magic-context
OpenCode plugin for Magic Context — cross-session memory and context management
- Tool@juspay/neurolink
The pipe layer of an AI nervous system: one interface connecting provider neurons to your application, across three inference types — generate, stream and decide. `decide
- Tool@mars-sea/dsh-commandcode-provider
Unofficial DeepSeek Harness LLM provider plugin for Command Code, ported from pi-commandcode-provider (MIT). Registers the 'commandcode' provider route with a Models-page
- Tool@thg-agentic/chatbot-sdk-react-native
React Native SDK for the THG AI Shopping Assistant — exports a single <Chatbot /> component that host apps can mount however they like.
- Toolveryfront
The simplest way to build AI-powered apps
- Tool@akropolys/kiku
The real-time conversational layer for the living web.
- Tool@moveo-ai/web-client
Client side library to load the moveo chat widget and connect it with your agent
- Tool@eddyskywalker/dsh-chatgpt-subscription
DSH provider plugin for Codex access through a ChatGPT subscription.
- Tool@lizard-build/cli
Lizard CLI — deploy apps, databases and sandboxes to Lizard (lizard.build) from your terminal or your coding agent. Detects Go, Node, Python, Rust, Ruby, PHP, Java and st
- Toolomnigateway
Self-hosted AI gateway with Anthropic- and OpenAI-compatible APIs, an admin console, and a CLI
- Tool@iobroker/mcp-server
MCP server for ioBroker
- Tool@qvac/sdk
**QVAC SDK** is the canonical entry point to develop AI applications with QVAC.
- Toolproject-agent-memory
MCP server for memory management using Qdrant vector database
Headlines and links come from the labs' own blogs, Hacker News and the GDELT news index, and from the sources our index already follows. We show a short excerpt and always link to the original. A launch reported by a news site rather than the lab is marked “Reported” until the lab itself announces it.