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@hcmai/sdk
TypeScript SDK for HCM Next business APIs, tenant delivery, and AI conversations.
- Toolomnius
AI coding agent powered by open-source models (Ollama/vLLM) — interactive TUI with agentic tool-calling loop
- Tool@soat/cli
CLI for SOAT — open-source infrastructure for production-ready AI agents.
- Tool@soat/sdk
TypeScript SDK for SOAT — open-source infrastructure for production-ready AI agents.
- Toolenclave-ai
AI agents that run in your user's browser: answers from documents, SQL over local data, and your own tools, with nothing sent to a server.
- Tool@sagentlab/navarch-runtime
Navarch machine-side session manager: claims delivery tasks and runs them through local coding agents.
- Tool@inkeep/open-knowledge
Local-first, agent-friendly Markdown knowledge base with a cross-platform CLI and web editor
- Toolcall-ai
Lightweight library for making AI API calls with streaming support
- Tool@bitfab/sdk
Bitfab client for provider-based API calls with local BAML execution
- Toolwiki-plugin-similarity
Federated Wiki plugin — semantic similarity search across wiki domains using prebuilt vector indexes
- Toolinline-chat-kit
An inline AI chat experience for React. The input is the message: it morphs into the bubble, the answer streams beneath it, and the parts around it — tool calls, reasonin
- Toolloki-mode
An autonomous software factory that knows what it is supposed to deliver, and proves it did.
- Tool@slopus/happy-providers
Stateful Node.js sessions for Codex, Claude, Grok, Bedrock, and Responses-compatible model providers.
- Tool@zhivex-ai/openai
OpenAI adapter for Zhivex AI SDK.
- Tool@zhivex-ai/core
Shared contracts and runtime helpers for Zhivex AI SDK.
- Toolloki-mode-sdk
TypeScript SDK for Loki Mode - autonomous multi-agent development platform
- Toolcode-auditor-mcp
Enforces architectural invariants and code quality rules inside your AI agent's edit loop.
- Toolai.libx.js
Unified API bridge for various AI models (LLMs, image/video generation, TTS, STT) - stateless, edge-compatible
- Toolfoxmemory
Local AI agent memory for JavaScript with semantic recall, editable records, IndexedDB and Node.js JSON storage, and foxmind embeddings.
- Tooldevlyn-cli
Loop & harness engineering for AI coding agents (Claude Code, Codex, and any AGENTS.md-driven agent) — core engineering principles for CLAUDE.md/AGENTS.md and a loop desi
- Tooleve
Filesystem-first framework for durable backend AI agents that run anywhere.
- Tool@tableau/mcp-server
Helping agents see and understand data.
- Tool@avakado.ai/token-dollars
USD pricing engine for LLM API usage. Pass a model id and a usage object, get a dollar cost.
- Toolneuro-vault-mcp
MCP server for semantic and lexical search over Obsidian vaults, with a self-built embedding index.
- Tool@framers/agentos
AgentOS: open-source TypeScript framework for autonomous AI agents. Unified graph orchestration, cognitive memory, runtime tool forging, multi-tier guardrails, voice pipe
- Tool@aeriondyseti/vector-memory-mcp
A zero-configuration RAG memory server for MCP clients
- Toolchamba
Run AI coding agents in a container, from your browser
- Tool@agentskit/doc-bridge
Human↔agent documentation bridge — deterministic handoffs, doc-site links, memory→docs, optional AgentsKit RAG/chat.
- Tool@respira/wordpress-mcp-server
WordPress MCP server + companion plugin giving AI native access to page builder content, not just the REST API. 252 tools, 356 with WooCommerce, 19 page builders and the
- Toolmyrmo-mcp
Myrmo MCP server: gives Claude Code, Cursor, Windsurf and any MCP client a shared memory of solved errors. Search fixes other AI agents found, report outcomes, publish ne
- Tool@softeria/ms-365-mcp-server
A Model Context Protocol (MCP) server for interacting with Microsoft 365 and Office services through the Graph API
- Tool@clipboard-health/playwright-reporter-llm
Playwright reporter that outputs structured JSON for LLM agents. Minimal console output, flat schema, easy to filter to failures.
- Toolopenfactor
Open Factor developer API CLI
- Tool@tangle-network/sandbox
Client SDK for the Tangle Sandbox platform - build AI agent applications with dev containers
- Tool@connexum/typescript-sdk
TypeScript SDK shim for My Compliance Center. Drop-in replacement for @anthropic-ai/sdk, openai, and @aws-sdk/client-bedrock-runtime with unavoidable governance enforceme
- Tool@stll/folio-agents
Framework-neutral LLM tool layer over folio's ai-edits engine: function-calling tools so an agent can read and mutate .docx documents through @stll/folio-core.
- Tool@payloadcms/plugin-mcp
MCP (Model Context Protocol) capabilities with Payload
- Toolalvin-bot
Self-hosted autonomous AI agent on Telegram, Slack, Discord, WhatsApp, Signal, terminal & web. Claude Agent SDK + multi-provider engine with auto-failover, detached sub-a
- Tool@sipemu/anofox-regression
Statistical regression library - WebAssembly bindings for anofox-regression
- 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
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.