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
- Toolhostinger-api-mcp
MCP server for Hostinger API
- Tool@kenz1117/dsh-engram
Cross-session long-term memory for DeepSeek Harness (memory palace · AGI Architecture Exploration on dsh-market): dual-scope SQLite memory graph, hybrid retrieval, proven
- Toolconverse-mcp-server
Converse MCP Server - Converse with other LLMs with chat and consensus tools
- Tool@felan-ai/felan
Felan Code: an open-source, model-portable coding agent built for cost-efficient, verifiable software work
- Tooldsh-claude-style
Claude Code Desktop theme for DeepSeek Harness (dsh) web GUI — visual & interaction overhaul
- Tool@azure/mcp
Azure MCP Server - Model Context Protocol implementation for Azure
- Tool@azure/mcp-linux-x64
Azure MCP Server - Model Context Protocol implementation for Azure, for linux on x64
- Tool@azure/mcp-win32-x64
Azure MCP Server - Model Context Protocol implementation for Azure, for win32 on x64
- Tool@azure/mcp-darwin-arm64
Azure MCP Server - Model Context Protocol implementation for Azure, for darwin on arm64
- Tool@utilix-tech/sdk
154+ developer utility tools for Node.js: JSON, encoding, hashing, color, CSS, network and more. Runs locally, no API key required.
- Tool@utilix-tech/mcp
MCP server exposing 198 Utilix developer tools to Claude, Cursor, VS Code Copilot, and any MCP-compatible AI assistant.
- Tool@nemesis-oss/ollama-sdk
Production-grade TypeScript SDK for Ollama with native fetch, high availability failover, multi-turn tool calling, structured outputs, reasoning stream tokens, OpenAI/Ant
- Tool@opencode-ai/models
Official typed client for the models.dev API — an open database of AI model capabilities, pricing, and limits
- Toolflagstaff
Spinners, progress, boxes and tables on one terminal frame loop, with a static projection for pipes, screen readers and agents, and a plugin host. No dependency outside t
- Toolcaique
Prompts that are flags first: an agent passes the answer up front, and a non-TTY caller gets an error naming the flag, never a prompt that waits. No dependency outside th
- Toolminutes-sdk
Conversation memory SDK — query meeting transcripts, decisions, and action items from any AI agent or application
- Toolsqlite-local-ai-memory
100% In-Process Bare-Metal Hybrid Memory Engine & MCP Server for LLMs (SQLite + Int8 Vectors).
- Toolkahoot-tools-ai-resocket-answer-tool
Kahoot Tools is a collection of useful utilities designed to enhance the Kahoot experience, simplify game management, and provide convenient tools for quizzes, learning,
- Toolbellpull
Runs a subprocess, resolves the executable it names, and returns one structured result every caller can read: a line for a person, a --json envelope or an agent event. Ze
- Toolintact-gateway
intact: a credential proxy for LLM providers, one base URL for every account
- Tool@aiquants/enrichment-drizzle
Drizzle ORM (mssql) models and types for storage metadata AI enrichment, chunks, system configurations, and the tri-store integrity audit's records.
- Toolintellivium-darwin-x64
Intellivium: framework de deep learning con núcleo en Rust, nativo de Node.js. Sin C/C++.
- Toolintellivium-linux-x64-musl
Intellivium: framework de deep learning con núcleo en Rust, nativo de Node.js. Sin C/C++.
- Toolintellivium-android-arm64
Intellivium: framework de deep learning con núcleo en Rust, nativo de Node.js. Sin C/C++.
- Toolintellivium-android-arm-eabi
Intellivium: framework de deep learning con núcleo en Rust, nativo de Node.js. Sin C/C++.
- Toolintellivium-linux-arm64-gnu
Intellivium: framework de deep learning con núcleo en Rust, nativo de Node.js. Sin C/C++.
- Toolintellivium
Intellivium: framework de deep learning con núcleo en Rust, nativo de Node.js. Sin C/C++.
- Toolintellivium-win32-x64-msvc
Intellivium: framework de deep learning con núcleo en Rust, nativo de Node.js. Sin C/C++.
- Toolintellivium-win32-arm64-msvc
Intellivium: framework de deep learning con núcleo en Rust, nativo de Node.js. Sin C/C++.
- Toolintellivium-linux-x64-gnu
Intellivium: framework de deep learning con núcleo en Rust, nativo de Node.js. Sin C/C++.
- Toolintellivium-darwin-arm64
Intellivium: framework de deep learning con núcleo en Rust, nativo de Node.js. Sin C/C++.
- Tool@sideboard-ai/cli
Sideboard CLI — agent-agnostic worktree orchestration (includes `sideboard mcp`)
- Tool@molecule/api-ai-embeddings-local
Local (offline) ai-embeddings provider for molecule.dev — runs a small sentence-embedding model in-process via Transformers.js (onnxruntime); no API key and no network at
- Tool@noir-ai/store
Noir store — embedded storage: better-sqlite3 + FTS5 (BM25, window snippets) + sqlite-vec (384-dim kNN).
- Tool@ai-sdk/openai-compatible
This package provides a foundation for implementing providers that expose an OpenAI-compatible API.
- Tool@noir-ai/context
Noir context — SHA-256 incremental indexer and hybrid retrieval (BM25 + vector kNN + Reciprocal Rank Fusion).
- Tool@starreel/mcp
StarReel MCP server — drive the AI short-drama production pipeline (script → storyboards → frames → video → final cut) from Claude, Cursor, or any MCP client
- Tool@ai-sdk/groq
The **[Groq provider](https://ai-sdk.dev/providers/ai-sdk-providers/groq)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the Groq chat an
- Tool@ai-sdk/google-vertex
The **[Google Vertex provider](https://ai-sdk.dev/providers/ai-sdk-providers/google-vertex)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support fo
- Tool@ai-sdk/xai
The **[xAI Grok provider](https://ai-sdk.dev/providers/ai-sdk-providers/xai)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the xAI chat
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.