Ross ROSS = Recommend OSS · open-source software intelligence for agents

vercel-labs/knowledge-agent-template

Some data may be outdated — see provenance labels.

Open source file-system and knowledge based agent template. Build AI agents that stay up to date with your knowledge base observed · 2026-10-02

github.com/vercel-labs/knowledge-agent-template · homepage · TypeScript · MIT (permissive) observed · 2026-10-02

Health v2 · maintenance only

59/100

  • Activity 95
  • Release rhythm 35
  • Longevity 19

Flags: no_releases

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-10-21. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 273
  • days_rel: n/a
  • days_push: 35
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

1065 stars · 137 forks observed · 2026-10-02

What it is AI-extracted, prompt v1, taxonomy v1, 2026-09-07, confidence 0.9

An open-source TypeScript (Nuxt/Vue) template for building file-system and knowledge-base based AI agents that search sources with grep, find, and cat instead of embeddings or vector databases. It ships with a chat UI, admin panel, complexity-based model routing, and pluggable adapters for deploying the same agent as a web chat, GitHub bot, or Discord bot.

Use cases

  • build an AI chatbot that answers questions from my documentation
  • deploy an agent that searches my knowledge base without embeddings
  • create a GitHub bot that answers issues using repo content
  • run a Discord bot backed by my own sources like YouTube transcripts
  • self-host a chat app over internal docs with an admin panel
  • plug custom APIs into an AI agent as searchable knowledge sources
  • reduce LLM costs by routing simple questions to cheaper models

When to choose

  • you want a ready-to-fork, deployable AI agent over a knowledge base
  • you prefer deterministic file-based search over maintaining a vector database and embedding pipeline
  • you need one agent deployed across multiple platforms (web, GitHub, Discord)
  • you want built-in admin tooling, usage stats, and cost-optimized model routing

When to avoid

  • you need semantic fuzzy matching that only embeddings provide
  • your knowledge base is unstructured data poorly served by text search
  • you need a non-JavaScript/TypeScript stack or a framework other than Nuxt/Vue
  • you want a fully managed SaaS rather than a self-hosted template

Facets

framework · maturity active

agent-framework rag chatbot search-engine web-framework chat-interface http-server artificial-intelligence chatbots developer-tools web-development self-hosted self-hosted cloud ai-agent-template knowledge-base no-vector-db file-system-search nuxt discord-bot github-bot chat-sdk vercel ai-agents nodejs typescript web-server docker

1 source

Member repositories

RepositoryRoleHealth v2
vercel-labs/knowledge-agent-templatemain59

For agents

markdown · JSON · MCP: product_card(name="vercel-labs/knowledge-agent-template")

Data as of 2026-10-19T08:05:51.212177+00:00 · Report a problem