← Back to Tanvrit AI
Documentation

Docs

Reference documentation for every developer-facing surface in Tanvrit AI. Want to skip ahead? Run the 5-minute quickstart.

Phase 2

Until search ships, every section below links to the relevant stub or live page.

5-minute quickstart

Install, index, wire up Claude Desktop, ask a question. No signup, no cloud.

Start →

Concepts

Phase 2

Local-first design, MCP protocol, indexer model, agent loop, conversation memory.

  • ▸What Tanvrit AI is (and isn't)
  • ▸Local-first vs cloud-first trade-offs
  • ▸How MCP fits into your editor / agent
  • ▸Indexer model: parsers, embeddings, SQLDelight schema
  • ▸Agent loop: ToolDispatcher + ConversationSummarizer

Installation

Open →

Get the desktop app, the VS Code extension, or the Wasm portal up.

  • ▸macOS (Apple Silicon + Intel)
  • ▸Windows MSI
  • ▸Linux DEB
  • ▸VS Code extension
  • ▸Wasm portal at /app/ (limited features)

Configuration

Phase 2

Settings file, bearer token rotation, telemetry, model selection.

  • ▸Settings → MCP Bearer Token
  • ▸Telemetry toggle (default OFF)
  • ▸AI provider keys (Claude, OpenAI, Gemini, Ollama, …)
  • ▸Indexer excludes and gitignore handling
  • ▸Database location and SQLite inspection

MCP server

Open →

JSON-RPC over HTTP / SSE on localhost:19281, stdio mode for trusted parents.

  • ▸Auth: Authorization: Bearer <token>
  • ▸Endpoints: tools/list, tools/call, resources/list, prompts/list
  • ▸Error model and retry semantics
  • ▸Resource templates and contextual prompts

Agent loop

Phase 2

How AgentLoop turns a user message into a sequence of tool calls.

  • ▸Plan → call tools → summarise → answer
  • ▸ConversationSummarizer for long sessions
  • ▸AgentToolRegistry mapping
  • ▸Stopping conditions and budget guards

Plugins

Phase 2

Extend Tanvrit AI with custom MCP tools and prompts.

  • ▸Tool plugin contract
  • ▸Prompt registration
  • ▸Loading order and conflicts
  • ▸Distribution (phase 2)

API reference

Open →

Full schema for MCP tools, request / response shapes, error codes.

  • ▸All 31 MCP tools (live list at runtime)
  • ▸Request schemas (JSON Schema)
  • ▸Response shapes
  • ▸Error taxonomy

Examples

Phase 2

End-to-end recipes: code review bot, refactor agent, dead-code finder.

  • ▸Refactor agent with Claude Desktop
  • ▸Dead-code finder via find_dead_code
  • ▸Reviewer with analyze_impact + git_history
  • ▸Custom HTTP client in 20 lines

Honest status

Sections marked "phase 2" are stubbed — the product ships them, but the long-form docs are still being written. The authoritative reference for tools is what your MCP client sees from tools/list at runtime.