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…
Monday 19 October
- Tool@promptowl/contextnest-engine
Core engine for governed, versioned, AI-ready context — selectors, hash-chain versioning, graph traversal, and integrity verification for LLMs and agents
- Tool@promptowl/contextnest-cli
CLI for governed, versioned, AI-ready context — versioned documents, deterministic queries, integrity verification, and MCP integration for AI agents
- Toolkorely-memory
JavaScript / TypeScript SDK for Korely Agents: memory for AI agents with bi-temporal typed facts.
- Tool@promptowl/contextnest-mcp-server
MCP server for governed, versioned, AI-ready context — gives Claude, Cursor, Gemini, Copilot, and Windsurf access to structured knowledge bases
- Tool@lasso-ai/cli
Select any part of your running app, describe a change, and let AI edit the real source code.
- Toolnano-lmcache
📚 An educational, step-by-step implementation of LLM KV cache reuse — learn prefix caching, chunk keys, storage & eviction, from pure Python to GPU tensors and vLLM inte
- Toolopenclaw-channel-gateway
OpenClaw IM channel gateway — bridge Telegram/Discord/WeChat/DingTalk/QQ to any OpenAI-compatible agent API
- Tool@rudderstack/ai
Automatic RudderStack AI product events and MCP server events for Node.js AI apps: OpenAI, OpenAI Agents, Anthropic, Google Gen AI, Amazon Bedrock, Vercel AI SDK, LangCha
- Toolmodel-orchestrator
Model router for AI coding agents: routes routine work to cheaper models with routing rules, 8 subagents, hooks and a CLI runner
- Tool@chat-adapter/gchat
Google Chat adapter for Chat SDK — service account auth, Card v2, dialogs, and Workspace Events
- Tool@chat-adapter/notion
Notion adapter for Chat SDK — participate in page and block comment discussions
- Tool@chat-adapter/linear
Linear adapter for Chat SDK — @mentions in issue comments and Linear agent sessions
- Tool@chat-adapter/whatsapp
WhatsApp adapter for Chat SDK — Business Cloud API webhooks, interactive messages, and templates
- Tool@chat-adapter/telegram
Telegram adapter for Chat SDK — Bot API webhooks, inline keyboards, reactions, and streaming
- Tool@chat-adapter/web
Web adapter for Chat SDK — browser chat UI over the AI SDK or AG-UI (TanStack AI) stream protocols
- Tool@chat-adapter/instagram
Instagram Direct Messages adapter for Chat SDK — native Meta Messaging API webhooks, media, and quick replies
- Tool@chat-adapter/x
X (Twitter) adapter for Chat SDK: reply to mentions, send direct messages, and post from your bot account with the X API v2, plus encrypted XChat conversations from the @
- Tool@chat-adapter/discord
Discord adapter for Chat SDK — HTTP interactions, Gateway events, slash commands, and embeds
- Tool@chat-adapter/slack
Slack adapter for Chat SDK — webhooks, Block Kit cards, OAuth, slash commands, and AI streaming
- Tool@chat-adapter/github
GitHub adapter for Chat SDK — respond to @mentions in pull request and issue comment threads
- Toolchat
Chat SDK — universal TypeScript toolkit for building multi-platform chat bots and AI agents on Slack, Teams, Google Chat, Discord, WhatsApp, and more
- Tool@chat-adapter/messenger
Facebook Messenger adapter for Chat SDK — Send API webhooks, templates, and quick replies
- Tool@chat-adapter/teams
Microsoft Teams adapter for Chat SDK — Bot Framework webhooks, Adaptive Cards, and Graph API
- Tool@chat-adapter/twilio
Twilio adapter for Chat SDK — SMS and MMS bots with Messaging webhooks and the Messages API
- Tooledge-cloud-vision
Edge-cloud vision with temporal memory, instrumentation, and calibrated per-condition acceptance (TFLite + MQTT + FastAPI/LLM).
- Tool@linxiraos/pi-ai
Unified LLM API with automatic model discovery and provider configuration
- Tool@crawlbrulee/mcp
official mcp server for crawlbrulee — EU-native web scraping for AI agents & developers. native scrape and map tools for your agent.
- Tool@richardmcquiston01/gemini-icon-gen
Generate style-consistent icons with Google's Gemini image API, the same way a Gemini "Gem" does — system instructions plus reference images in, a matching icon out.
- Toolgrcskills
Open GRC skills for AI agents. By ISMS Copilot.
- Tooljules-orchestrator-kit
Zero-dependency safety gatekeeper, test oracle generator, and multi-agent coordination protocol for autonomous coding agents — Google Jules, Claude Code, Codex and Gemini
- Toolalpic
The command-line interface for Alpic
- Tool@goplus/agentguard
GoPlus AgentGuard — Security guard for AI agents. Blocks dangerous commands, prevents data leaks, protects secrets. 20 detection rules, runtime action evaluation, trust r
- Tool@superagnt/exa-search
OpenClaw plugin for Exa — run neural web search, fetch parsed contents, find similar URLs, and get agentic answers through your superagnt API key.
- Tool@2kw/ai-mcp-server
MCP server for 2kw.ai — EU-hosted AI platform: OpenAI-compatible LLM gateway, schema-driven document extraction, transcription, agents with a knowledge base, and cost obs
- Toolagentic-qe
Agentic Quality Engineering V3 - Domain-Driven Design Architecture with 13 Bounded Contexts, O(log n) coverage analysis, ReasoningBank learning, 60 specialized QE agents,
- Tool@prevalentware/opencode-goal-plugin
OpenCode goal plugin that adds Codex-style long-running goal mode, /goal commands, persistence, and TUI status for AI coding agents.
- Tool@freibergergarcia/phone-a-friend
CLI relay that lets AI coding agents collaborate
- Tool@automatelab/n8n-mcp
MCP server for n8n with tools for generating workflows, linting, diagnosing failed executions, and driving live n8n instances. Built for AI agents.
- ToolOpen-Hermes-Bot
Hermes Bot — a native Mac interface to the Hermes agents you already have.
- Tool@aikdna/kdna-cli
KDNA CLI: bounded authored input, native asset creation, exclusive saving and explicit local Read disclosure.
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.