Skip to content
In development

Kova — Durable Execution Engine for AI Agents

A WAL-First agent engine built in Rust — auto-recovers from crashes, 3μs scheduling

3.17μsFIFO schedulingCriterion full pipeline
315K ops/sThroughput
178K LOCCodebase21-crate workspace
ZeroExternal depsNo Redis / Postgres

What is Kova?

Kova is Lurus’s core AI Agent infrastructure — a high-performance, durable execution engine built in Rust. It solves how agents reliably run for long periods, recover their state after a crash, and coordinate complex workflows. Traditional frameworks (LangChain, CrewAI) run in memory, so state is lost the moment the process exits. Kova adopts a WAL (Write-Ahead Log)WALWrite-Ahead Log. Every state change is written to the log before it executes, ensuring recovery from the log after a crash.Learn more →-first architecture: every execution step is persisted as a record, so even after a crash it can recover precisely to the point of interruption — without re-calling the LLM, losing progress, or incurring extra cost.

Key metrics

FIFOFIFOFirst In, First Out. Kova's task scheduling uses a FIFO strategy by default. full-pipeline latency of 3.17μs (Criterion benchmark, see docs/benchmark-report.md), 315K ops/s throughput, and zero external service dependencies.

Core capabilities

Why choose Kova

WAL-First durability, microsecond-scale scheduling, zero-dependency deployment, and four access methods.

WAL crash recovery

Write-ahead log + CRC32 checksum per step; replays from the breakpoint after a crash, without re-calling the LLM

3μs scheduling latency

FIFO full-pipeline Criterion benchmark of 3.17μs, 315K ops/s throughput

Zero external dependencies

No Redis / Postgres required; runs with just a local WAL file

Four access methods

Rust SDK / gRPC / REST / MCP, modularized across a 21-crate workspace

WAL-First durability

All state changes are written to the WAL before they execute; on a crash, state is replayed from the WAL:

  1. Agent decision — the engine determines the next action

  2. WAL write (CRC32) — persists a record + checksum to guard against corruption

  3. Execution — actually invokes the tool / LLM

  4. Completion confirmed — marks the step as committed; on a crash, unconfirmed steps are automatically replayed

CRC32 checksums guard against corruption; a power-of-2 ring buffer makes efficient use of storage; and a strict Buffer → Queue → Txn lock order guarantees freedom from deadlock.

Agent orchestration

ModeDescriptionUse cases
Single agentExecutes a task independentlySimple automation
WorkflowMulti-step ordered executionData pipelines, approval flows
SwarmMultiple agents collaborating autonomouslyComplex research, multi-role simulation

Tool ecosystem and multi-model support

Tool ecosystem

Built-in tools (file / HTTP / database / shell), MCPMCPModel Context Protocol — an open standard that lets AI agents call external tools and data sources in a uniform way.Learn more → (connect to any MCP-compatible tool service, see the integrations directory), A2AA2AThe Agent-to-Agent protocol, which lets multiple agents communicate directly, delegate tasks, and exchange information. (direct agent-to-agent communication and task delegation), and custom tools (extend via Rust or a REST API).

Multi-model support

Access all mainstream LLMs through the Lurus API (DeepSeek for everyday use / GPT-4o for reasoning / Claude for long contexts / Gemini for multimodal), switching dynamically per task at runtime.


Architecture

Architecture overview

REST/SDK/gRPC/MCP access · Kova Core scheduling · WAL durability and recovery.

Kova execution architecture
Kova REST API (Axum: 35+ endpoints, WebSocket)
 → Kova Core: Agent Engine(单/多 Agent) + Workflow(有序编排)
              → WAL + Ring Buffer(持久化状态管理 CRC32)
              子 crate: kova-llm / kova-tools / kova-mcp

Kova is a workspace of 21 Rust crates, 178,284 lines of code, and 1,565+ tests (loom concurrency / proptest / chaos) plus 4 fuzz targets. It is currently a v0.2.0 pre-release (heading toward 1.0.0-beta.1), with strict lints fully enabled (#[deny(clippy::unwrap_used, clippy::panic, missing_docs)]).


Scenarios

Where Kova fits

ScenarioKova’s advantage
Long-running agentsWAL durability with automatic recovery after a crash
Complex workflowsMulti-step orchestration, conditional branches, parallel execution
Multi-agent collaborationSwarm mode with direct agent-to-agent communication
Enterprise deploymentRust performance, low resource footprint, no GC pauses
MCP tool integrationNative support for the Model Context Protocol
Security-sensitive scenariosOptional encryption (SM4/AES), WAL HMAC integrity verification

Get started by role

  1. DeveloperSpin up a durable agent in 5 minutescargo add kova + 3 lines of code
  2. ArchitectReplace the LangGraph CheckpointerUse Kova to store checkpoints in a LangGraph project

Comparison

Compared with other agent frameworks

CapabilityLangChainCrewAIAutoGenKova
LanguagePythonPythonPythonRust
State persistenceNone (needs external)NoneNoneWAL-First
Crash recoveryNoneNoneNoneAutomatic recovery
PerformanceMediumMediumMediumVery high
Memory efficiencyLowLowLowVery high
MCP supportThird-partyNoneNoneNative
A2A protocolNoneNoneNoneNative
EncryptionNoneNoneNoneSM4-GCM / ChaCha20
Multi-protocolNoneNoneNoneFour access methods: Rust SDK / gRPC / REST / MCP
Deployment formPython processPython processPython processSingle binary / container / embedded library

Next steps

Next steps

Powered by Lurus Technologies