Skip to content
VENKAI
Pilot

Integrations

Use Venkai with your existing stack.

Every row carries a status and the evidence behind it. "Compatible by architecture" means no official integration exists and nothing has been tested.

Where it plugs in

Next to what already runs

  1. 01ApplicationYour product, unchanged.
  2. 02Agents and stepsYour orchestrator, models, memory and RAG stay where they are.
  3. 03Venkai — REST · SDK · MCPCalled by the agent, next to those systems rather than underneath them: read before the prompt, write after the decision.
  4. 04Typed work stateFact, decision, constraint, preference, event, relationship — versioned, isolated per organization.
  5. 05Work continuesThe next agent, session or model resumes from that state.

Legend

Four statuses, never mixed

  • Supported

    Official interface, documented, covered by tests.

  • Tested

    Actually exercised with Venkai, with a named piece of evidence.

  • Compatible by architecture

    Nothing in the architecture prevents it. No official integration, no test.

  • Planned

    On a dated roadmap. No integration is on it today.

Status

Venkai interfaces

SystemStatusWhat is actually verified
REST APISupportedDocumented (/api/memory, /api/context/{project}/relevant). Covered by tests/test_api.py.
Python SDKSupportedremember / recall / decisions / timeline. Covered by tests/test_sdk.py and the handoff demo (19/19).
MCP (stdio)TestedBeta. Covered by tests/test_mcp.py; used daily by Claude Code inside the founder's own agent system.

Status

Memory

SystemStatusWhat is actually verified
Mem0Compatible by architectureNo adapter, no test. An agent can call both in the same step; nothing in Venkai assumes or excludes this system.
ZepCompatible by architectureNo adapter, no test. An agent can call both in the same step; nothing in Venkai assumes or excludes this system.
LettaCompatible by architectureNo adapter, no test. An agent can call both in the same step; nothing in Venkai assumes or excludes this system.
Custom memory systemsCompatible by architectureVenkai is two HTTP calls and depends on no other store. Not tested with a third-party system.

Status

Orchestration

SystemStatusWhat is actually verified
LangGraphCompatible by architectureDocumented pattern: a node before the model loads context into state, a node after it writes conclusions. No package, no test.
CrewAICompatible by architectureDocumented pattern: a task callback, or a custom tool the agent calls. No package, no test.
AutoGenCompatible by architectureNo documented pattern, no test. Same principle: read before the prompt, write after the decision.
Custom orchestratorsTestedThe documented loop (load before the prompt, record after the decision) runs in the A → B → C handoff demo: 19/19 checks, real API server, Python SDK.

Status

Models

SystemStatusWhat is actually verified
ClaudeTestedThrough Claude Code and the MCP server, in daily in-house use. Not through the Anthropic API directly.
GPTCompatible by architectureVenkai calls no model and returns JSON. No agent running this model has been tested against Venkai.
GeminiCompatible by architectureVenkai calls no model and returns JSON. No agent running this model has been tested against Venkai.
Local modelsCompatible by architectureVenkai calls no model and returns JSON. No agent running this model has been tested against Venkai.

Priorities

What decides the next integration

No integration gets built on intuition. The order will follow two signals: the stacks described in pilot requests, and measured interest on this page and in the FAQ. If your stack is missing or only compatible, say so in the pilot request — that is exactly the signal.

Tell us which stack you run.

Memory, orchestrator, models, and where context gets lost. We answer with a pilot scope, or with the reason Venkai isn't the right piece.

Describe your stack