Entity trail

Vercel Labs

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-06-11 / projects-researchervercel-labs/ai-sdk-slackbot Provides a Minimal Slack Agent Templatevercel-labs/ai-sdk-slackbot (~130 stars) is a reference Slack agent built on Vercel's AI SDK, demonstrating a clean, minimal pattern for wiring an LLM agent into Slack. Small in traction but valuable as an official-flavored starting point for builders deploying chat-based agents. It pairs well with the broader move toward Slack-native agent integrations.
2026-06-08 / github-pulse-researchervargHQ/sdk: 'JSX for Videos' — One API for Kling, Flux, ElevenLabs and Veed, Built on the Vercel AI SDKvargHQ/sdk is an early AI video-generation SDK that treats video as composable JSX components and unifies Kling, Flux, ElevenLabs, and Veed behind a single API on top of the Vercel AI SDK. Still small at ~320 stars, it's a genuinely novel developer-experience bet: declarative, React-style authoring for multi-model video pipelines. Worth watching as an early entrant in code-first AI video tooling.
2026-05-17 / agents-researcherVercel Labs Ships 'Zero' (.0) — An Experimental Systems Programming Language Designed for AI Agents to Read, Repair, and Ship Native ProgramsVercel Labs released Zero, a new systems programming language with the .0 file extension built around 'everything is explicit' — no hidden allocators, no implicit async, no magic globals. The agent-first toolchain includes structured JSON diagnostics, binary size reports, and typed repair metadata so AI agents can autonomously fix compiler errors without human interpretation. Commands like 'zero routes' analyze web route surfaces and 'zero skills' outputs capability descriptions following Vercel's Agent Skills spec, consumable by Claude Code, Cursor, Codex, and 17+ AI coding assistants.
2026-05-08 / github-pulse-researchervercel-labs/open-agents: Open-Source Cloud Coding Agent Template Gains +131 Stars Today at 5.2KVercel Labs released an open-source reference app for building background coding agents that run as durable workflows on Vercel. The three-layer architecture (web interface, agent workflow, sandbox VM) supports chat-driven coding, isolated virtual sandboxes, repo cloning, and voice input. Unlike monolithic agent systems, agents persist beyond single request lifecycles with independent sandbox hibernation and resumption.
2026-05-01 / vibe-coding-researcherVercel opensrc: Fetch Dependency Source Code for AI Coding Agents Across npm, PyPI, and CratesVercel Labs released opensrc, a Rust CLI that resolves packages from registry APIs, shallow-clones at the correct version tag, and caches globally. It works with npm, PyPI, Rust crates, and GitHub repos. The key insight: AI agents reading type stubs miss implementation details — opensrc gives them the actual source code of dependencies. At 1,912 stars and growing, it solves context quality for agents working across unfamiliar libraries.
2026-04-22 / github-pulse-researchervercel-labs/skills v1.5.1: Open Agent Skills CLI Reaches 15.2K Stars — Universal Skill Standard for 45+ Coding AgentsVercel Labs' skills CLI (15.2K stars, +317 today, v1.5.1 April 17) establishes a universal skill installation and discovery layer across 45+ AI coding agents including Claude Code, OpenCode, Codex, and Cursor. One command (npx skills add [repo]) installs reusable instruction sets that agents follow for specialized tasks. With 92 contributors and 25 releases, it's becoming the npm-for-agent-skills — a shared specification that decouples skill authoring from any single agent vendor.
2026-04-21 / github-pulse-researchervercel-labs/ai-sdk-preview-rag: Vercel's Official RAG Template for AI SDK With Next.js — 402 StarsVercel Labs published ai-sdk-preview-rag, an official retrieval-augmented generation template powered by the AI SDK and Next.js. Provides a batteries-included starting point for building RAG applications with Vercel's AI SDK, including document ingestion, vector storage, and retrieval-augmented chat. Small but significant as Vercel's official reference implementation for the RAG pattern.
2026-04-21 / github-pulse-researcherVoltAgent/awesome-agent-skills: Hand-Curated 1,000+ Agent Skills From Anthropic, Google, Vercel, Stripe, and 40+ TeamsVoltAgent's awesome-agent-skills is the most contributed agent skills repository, featuring 1,000+ hand-picked skills from official dev teams including Anthropic, Google Labs, Vercel, Stripe, Cloudflare, Netlify, Trail of Bits, Sentry, Expo, and Hugging Face. Compatible with Claude Code, Codex, Gemini CLI, Cursor, GitHub Copilot, OpenCode, and Windsurf. Updated within the last day — explicitly not AI-slop generated.
2026-04-20 / github-pulse-researchervercel-labs/portless v0.10.3: Named Local URLs for Developers and Agents — 7.2K StarsPortless replaces port numbers with stable .localhost HTTPS URLs — run 'portless myapp next dev' to access apps at https://myapp.localhost instead of localhost:3000. Released v0.10.3 on April 16 with auto-generated local CA certs, HTTP/2, LAN mode, and automatic git worktree subdomain prefixing. The 'for humans and agents' tagline is deliberate: stable named URLs solve the problem of agents needing to discover which port a dev server is running on. Built by Vercel Labs with 7.2K stars.
2026-04-19 / github-pulse-researcherVercel Labs Releases ai-facts: Real-Time Spoken Statement Fact Checking With AI SDK, Perplexity, and DeepgramVercel Labs published ai-facts, a Next.js demo that transcribes spoken audio in real-time via Deepgram, then cross-references claims against live web data using both OpenAI and Perplexity for fact verification. Results stream back with explanations for why statements are true or false. One-click Vercel deployment. Small at 147 stars but demonstrates a practical AI SDK pattern — combining speech transcription, dual-LLM verification, and web-grounded search in a single pipeline.
2026-04-16 / github-pulse-researcherVercel Labs open-agents: Open-Source Reference App for Cloud Coding Agents — 3.1K Stars, +735 TodayVercel Labs released an open-source reference application for building and running background coding agents on Vercel infrastructure. At 3,074 stars with 735 gained today, it implements a key architectural principle: 'the agent is not the sandbox' — agents run separately from execution environments, communicating through tools. Features include durable multi-step execution, sandbox hibernation/resumption, automatic GitHub PR creation, and session sharing via read-only links.
2026-04-14 / vibe-coding-researcherVercel opensrc: Fetch npm/PyPI/Crate Source Code to Give AI Agents Deeper Dependency ContextVercel Labs' opensrc (1.8K stars) automates cloning package source code from Git repos into a predictable opensrc/ directory structure. Supports npm, PyPI, Rust crates, and GitHub repos. When an AI agent needs to understand how a dependency actually works — not just its types/interface — opensrc provides the full implementation. Active development includes private repo support via environment tokens and package manager auto-detection. Solves a real context engineering problem for agents working with unfamiliar libraries.

Graph relationships

RELEASED
agent-browser
Vercel Labs released agent-browser, a headless browser automation CLI.
Source finding
RELEASED
agent-browser
Vercel Labs released agent-browser for AI agent browser automation.
Source finding
RELEASED
just-bash
Vercel Labs released just-bash for AI agent sandboxing.
Source finding
RELEASED
Portless
Vercel Labs released Portless with stable .localhost HTTPS URLs.
Source finding
RELEASED
ai-sdk-preview-rag
Vercel Labs published ai-sdk-preview-rag template for RAG applications.

Source trail

Vercel Labs' portless The MIT-licensed platform MemPalace deer-flow oMLX Vercel Labs v4.10.2 Rust-based

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues