Anvaya CLI · THE EXECUTION LAYER

The Terminal ThatKnows Your Codebase.

One Rust binary, zero runtime dependencies. Run it as a full-screen TUI or headless in a pipeline. It talks to Ollama by default, so the whole loop can run on your machine. It’s the execution half of Anvaya: every turn is packed with memory from Anvaya Mind → and reports back what it learned, the same memory Claude Code and other agents can read over MCP.

ANV, HEADLESSanv 0.1.0

$anv init

✓ .anvaya/ initialized

$anv -m devstral:latest -p ollama

Keys 1-7 switch panels, Tab cycles, Y/N approves

By The Numbers

What’s Actually In It.

11Crates in the workspace, ~40K lines of Rust

18Native tools, no plugin layer, no shelling out to Python

4Providers: Ollama, Anthropic, OpenAI, Siemens

500+Tests across the workspace

Seven Panels, One Keystroke Apart.

Everything the agent is doing stays visible. The terminal panel runs a split-tree workspace, so you can keep a build running beside the agent without leaving the TUI.

1 AgentThe main loop, prompt, streamed reasoning, tool approvals.

2 GitStatus, diff, and file navigation without leaving the TUI.

3 MonitorLive view of the Mind daemon: workers, sockets, graph size.

4 MCPBrowse tools exposed by connected MCP servers.

5 Mind VizThe knowledge graph rendered, nodes, links, weights.

6 TerminalSplit-tree multi-pane shell. Ctrl+A toggles pane-command mode.

7 StartupModel, provider, and project resolution before the first turn.

Eighteen Tools, All Native.

Every tool is compiled into the binary. Destructive ones route through an approval gate unless you pass --yolo; --plan-only disables writes and execution entirely.

read_fileRead with range support

edit_fileTargeted string replacement

rewrite_fileFull-file replacement

patchApply a unified diff

globMatch paths by pattern

grepSearch file contents

search_in_fileScoped in-file search

list_dirDirectory listing

dir_treeRecursive tree view

create_file_or_folderCreate paths

delete_file_or_folderRemove paths

run_commandShell execution, gated by approval

todowriteTrack multi-step work

webfetchFetch and read a URL

websearchSearch the web

lspLanguage server queries

questionAsk the user before proceeding

taskDelegate to a sub-agent

Every Turn Is A Loop, Not A Prompt.

Between your input and the model sits a four-stage harness. The last two stages are what make memory compound, the loop closes back into Mind instead of ending at the reply.

01Intent EngineClassifies what the turn is actually trying to do before any context is assembled.

02Context PackerRequests memory from Mind under a token budget and packs it against the prompt.

03Turn LearnerRecords which injected nodes the turn actually touched, and the outcome, then sends it back.

04Session SynthesizerCondenses the finished session into durable nodes rather than a raw transcript.

It Runs Without You Watching.

Drop --no-tui and it becomes a normal Unix citizen: reads a prompt, writes to stdout, exits with a meaningful code. 0 on success, 1 on error, 2 when an approval was denied.

ANV, CI MODEstdin / stdout

$anv --no-tui --plan-only "what would change to add Redis caching?"

# read-only, never writes, never executes

$anv --no-tui --yolo "fix the auth bug in src/auth.rs"

$anv -s list

# resume any prior session by code, or --continue for the last one

Stop Starting From Zero.

One binary. 11+9 Rust crates. 545 tests. Hand-written HNSW index. Three transport modes. Four providers, Ollama, Anthropic, OpenAI, Siemens. Zero API keys required to start. Mind remembers everything after the first session.

Get Started →Read the FAQ