Your team's knowledge,
finally findable.

Issues, wiki, documents, and attachments — connected in one searchable knowledge graph, for your team and your AI agents.

  • Partial reads & edits — fewer agent tokens
  • Runs fully air-gapped
  • AGPL open source

Where knowledge comes together.

A full tracker, a versioned wiki, hybrid search, and flexible metadata — one connected workspace for your team and your agents.

Specivo kanban board with New, In Progress, Resolved and Feedback columns; issue cards show refs like ACME-42, tracker types (Feature, Bug, Task), priority dots and assignee avatars.
Tracking

Issues & tracking

A full issue tracker — types, statuses, priorities, assignees, subtasks, and dependencies between issues. Plan with sprints, see the whole release on a roadmap, and switch between list and board views.

A Specivo wiki article rendered from Markdown, with a page hierarchy in the sidebar and version history controls.
Knowledge

Team wiki

A versioned Markdown wiki with full history and one-click revert, page hierarchy, and cross-links straight to issues. Knowledge that outlives the people who wrote it.

Specivo hybrid search results page with a Hybrid/Keyword toggle and type filters for Issues, Wiki, Comments and Attachments; results show titles, project chips and matching snippets.
Search

Hybrid search

Keyword and semantic search together, across issues, wiki, comments, and attachments. It finds work by meaning, not just exact words — search “login flow” and it surfaces the page that says “auth sequence.”

An issue in Specivo showing typed metadata fields such as story points, git branch and severity attached alongside the standard issue details.
Metadata

Flexible metadata

Typed metadata schemas that hold whatever your team needs — story points, git branches, severity, content status — defined per project or per issue type. More flexible than rigid custom fields, without the bolt-on feel.

Coming from Asana, Monday, or Jira?

Here's why teams move their work into Specivo.

Self-hosted — own your data

Runs on your servers, even fully air-gapped. Nothing leaves your network.

No per-seat pricing

Add your whole team and your AI agents. You're not billed per user.

Open source (AGPL)

Inspect it, extend it, fork it. No lock-in and no black boxes.

Built for AI agents

A built-in MCP server lets Claude Code, Codex, and others work the same issues and wiki as your team — reading a single wiki section or updating one field instead of the whole page. Fewer tokens, and every action is audited.

One tool, not five

Tracker, wiki, search, and docs in one place — instead of stitching Asana, Confluence, and a search add-on together.

Everything's connected & searchable

Issues, wiki, comments, and attachments link together — and all of it is found by one hybrid search.

Built for humans and AI agents.

Most tools are built for humans. Some are built for AI. Specivo is built for both.

AI agents read the same wiki, update the same issues, search the same knowledge base. Every action is tracked — who did what, human or AI, with full context. When you need to know what happened, you don't ask. You search.

Works with your AI tools.

Specivo ships with a built-in MCP server. Tested with Claude Code and Codex. Works with any tool that supports the MCP protocol.

One config line, and the agent stops guessing and starts looking things up.

// Add to your AI tool's MCP config:
{
  "mcpServers": {
    "specivo": {
      "url": "http://localhost:8000/mcp",
      "apiKey": "spv_your_key_here"
    }
  }
}
Claude Code Codex + any MCP client

AI is optional. Always.

Specivo works perfectly without AI. When you're ready, enable it with one toggle—using a free local model or your own API key. Your choice.

Local

Ollama

Free. Air-gapped. No internet needed.

BYOK

Your API Key

Your OpenAI/Anthropic key. Your cost. Your data.

Your data. Your server.

No per-seat pricing. No user limits. Your team of 3 or 3,000 — same cost: zero.

AGPL licensed. No cloud dependencies. Your infrastructure, your rules.

More from Specivo.

Open-source tools we build alongside the platform.

django-seo-suite

Django

A lightweight, extensible SEO metadata layer for Django — titles, meta tags, canonical URLs, hreflang alternates, JSON-LD schema, and Open Graph/Twitter cards across models and views, plus a versioned robots.txt. One consistent API, no extra dependencies.