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 12 October
- Toolnestjs-langchain
NestJS library to build agents with LangChain
- Tool@forumone/throughline
Throughline: an editorial platform for Payload CMS. Publishing, approvals, audit, integrations, email and jobs, with every feature reachable over MCP.
- Tool@forumone/throughline-design-system
The design-system side of Throughline: the component contract and manifest a design system publishes, its linter, and the Payload blocks, rendering and admin components g
- Tool@simem/cli
simem — Super Intelligence Memory for AI coding agents: spend fewer tokens in the Claude Code and Codex apps, and keep project memory across every account, agent, and wor
- Toolsensemaking
Query and search your markdown notes with context-aware progressive disclosure: SQL over frontmatter, links, and text, plus semantic search and link-graph ranking. No ser
- Tooldsh-web-search-enhanced
Session-scoped search connections for DeepSeek Harness
- Tool@ndokutovich/arca
Keep the raw transcript. A local-first vault for coding-agent history — transcripts verbatim in git, indexed for hybrid search, served over MCP.
- Tool@execlave/sdk
Official JavaScript/TypeScript SDK for the Execlave AI agent governance platform — tracing, policy enforcement, and framework auto-instrumentation for LangChain, OpenAI A
- Toolrsi_eval
A lightweight Python SDK and CLI for evaluating recursive self-improvement (RSI) methods across agent benchmarks.
- Tooldocusaurus-plugin-copy-page-button
Docusaurus plugin that adds a copy page button to extract documentation content as markdown for AI tools like ChatGPT, Claude, Perplexity, and Gemini
- Tool@viveka10/cap-ai-token-optimizer
SAP CAP plugin to reduce, measure and report SAP AI Core LLM token usage: prompt optimization, response cache, cost tracking, a built-in usage dashboard, and metrics for
- Tool@kipachu/omem
Obsidian-vault-first memory for AI agents: hybrid vector + keyword + graph retrieval over markdown, MCP server, git auto-sync
- Tooln8n-nodes-route33-lm
n8n chat model sub-node for the Route33 custom AI router
- Toolgenrelay
JavaScript/TypeScript client for the GenRelay generative media API: video and image generation with Veo 3.1, Grok Imagine, Nano Banana and GPT Image 2
- Tool@decodo/langchain-ts
LangChain tools for Decodo's Scraper API
- Toolairgpt
train your own chatbot from scratch on a mac
- Tool@cyanheads/mcp-ts-core
Agent-native TypeScript framework for building MCP servers.
- Toolriver-bulk-apikey
Bulk-create River AI (console.river.ai) accounts with auto-generated API keys, driven through a real cloud browser over CDP. Zero dependencies. OpenAI-compatible inferenc
- Tooleslint-plugin-vercel-ai-security
ESLint plugin for Vercel AI SDK security — detects prompt injection, system-prompt leaks, hardcoded API keys, and unvalidated model output in generateText and streamText.
- Toolkoishi-plugin-toutai
Koishi 插件：随机投胎模拟，模拟降生中国与世界的各项人生结果，并查看记录与排行榜。
- Tool@vectorize-io/hindsight-eve
Hindsight memory provider for Vercel Eve agents — scoped recall before each turn, automatic capture after, and a reflect tool
- Toolskald
Every visit, truly told. Self-hosted web analytics from your server access log: see people, AI assistants (ChatGPT, Claude, Perplexity), crawlers and bots that JavaScript
- Toolbuggazi
Buggazi CLI - project management for coding agents. Bug tracking, feature planning, sprint management. As easy as git.
- Tool@ohos-ports/ruv-swarm
High-performance neural network swarm orchestration in WebAssembly
- Toolai-slop-detector
120 patterns that make writing read like AI slop, with an agent skill for Claude Code and Codex.
- Toolllmock
A configurable mock LLM API server for testing and development
- Toolsolid-glass
A design system for AI applications. Material, physical, tactile, technical.
- Toolmodelplan
Which AI coding model, at which effort, on which plan? Recommended efforts, a leaderboard at those efforts and plan advice from modelplan.ai, in Claude Code, Codex and th
- Toolskipverse
A from-scratch vector database: HNSW approximate nearest neighbor index, zero runtime dependencies, crash-safe WAL, deterministic replay, and a living search visualizatio
- ToolDishwasherBench
A dishwasher-loading game on a physical simulation of one real machine, built to benchmark language models and playable in a browser. The game inside is called Spotless.
- Toolcrazyrouter
OpenAI SDK wrapper for Crazyrouter with configurable API base and chat/model helpers
- Toolmidnight-wallet-cli
Git-style CLI wallet for the Midnight blockchain
- Tool@atlasauth/pca-langchain
LangChain adapter for Proof-Carrying Authority: wrap a StructuredTool so every invocation emits a PCActn (and attaches the proof) before the tool runs.
- Tool@atlasauth/pca-rag
FGA-for-RAG for PCA: retrieval-time, per-principal document filtering driven by the PCA policy engine, with the filtering decision captured in the proof trace (provable:
- Toolhivehouse
An agent hub for Claude Code: one hub runs teams of Claude Code agents across all your projects, with delegate mode, reviews and gates.
- Tooldsh-skill-trace
DSH Skill 智能实验室（DSH Skill Intelligence）：探索优秀 Agent Skill 的结构与方法，将成熟 AI 工作流转化为个人能力和企业业务能力。
- Toolnew-term-radar
Daily radar for new AI terms: names of new models, products and repos, caught on X, Hugging Face, GitHub and sitemaps before keyword tools list them.
- Toolcodebase-semantic-search
Local semantic search engine for any codebase. MCP + HTTP + file watcher. Reuses Ollama embeddings + Milvus vector storage.
- Toolbruce-md2word
面向 AI Agent 的 Markdown 转 Word 工具，提供开箱即用的中文排版、Mermaid 图表转图片和可编辑数学公式，提供Skill、独立 CLI 和 DSH 插件。
- Toolsession-intelligence
Help individuals and teams understand their prompting habits and improve how they work with AI coding agents. Get specific insights into prompt clarity, context, rework,
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.