Vs · OpenCode

Anvaya vs OpenCode.

The open-source multi-provider TUI with 75+ models — against the Rust agent that remembers. Same spirit, different bet.

Direct answer

Anvaya vs OpenCode: both are terminal agents that refuse model lock-in — OpenCode routes 75+ providers through a TypeScript TUI (plus desktop and IDE extensions), Anvaya runs Ollama-first with Anthropic, OpenAI, and custom gateways from a single ~15MB Rust binary. The split is memory: OpenCode keeps checkpoint summaries, so session 50 costs what session 1 cost; Anvaya keeps a compounding knowledge graph (typed nodes, decay, drift detection, outcome calibration) packing 2–4K tokens instead of ~50K raw. OpenCode wins on provider breadth, surface coverage, and MIT openness today; Anvaya wins on local footprint (~5MB idle, no runtime), code-native retrieval (repomap PageRank + pooled LSP), and context that improves with use. Anvaya is pre-1.0 and proprietary — OpenCode is the mature open default; Anvaya is the memory bet.

The Table

Side by Side.

DimensionOpenCodeAnvayaWinner
Providers75+ via Models.devOllama + 3 + customOpenCode on breadth
Memory modelCheckpoint summaryTyped graph, calibratedAnvaya on compounding
SurfacesTUI + desktop + IDETUI + headless CIOpenCode on coverage
FootprintTS runtime + extensions~15MB binary, ~5MB idleAnvaya on weight
LSPNativeNative pooled sessionsTie
LicenseMIT open sourceProprietary (pre-1.0)OpenCode on openness
Local modelsVia Ollama endpointsOllama-first, offlineAnvaya on local

Questions

Asked About the Two.

Q

How is Anvaya different from OpenCode?

OpenCode is the most flexible open-source harness: 75+ providers, subagents, plan mode, LSP — bring any model. Anvaya shares that philosophy (multi-provider, subagents, plan mode, native LSP) and adds what OpenCode lacks: a persistent memory graph that compounds across sessions, repomap PageRank retrieval, and a ~15MB single Rust binary with ~5MB idle.

Q

Can I use OpenCode's models with Anvaya's memory?

Conceptually yes: Anvaya is multi-provider (Ollama, Anthropic, OpenAI, custom gateways), so the same Claude/GPT/Gemini keys work. During beta the practical bridge is MCP — serve Anvaya's memory to any harness while the native multi-provider loop hardens.

Q

Which is lighter?

Anvaya: one ~15MB Rust binary, ~5MB idle, no runtime. OpenCode ships a TypeScript TUI plus desktop and IDE extensions — broader surface, heavier footprint. Pick OpenCode for surface coverage, Anvaya for minimal local footprint plus memory.

Q

Is Anvaya open source like OpenCode?

Anvaya is pre-1.0 and proprietary-licensed; OpenCode is MIT. What Anvaya offers instead of source access is inspectability: every tool, node, and context decision is visible and debuggable, and the memory files are open formats (SQLite, flat index, NDJSON log).

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