What is context engineering?

Context engineering is choosing what goes into the model's context window on every turn (instructions, history, retrieved knowledge and tool results) so the agent stays accurate without overflowing or overspending.

Open source + Enterprise

How AgentOven does it

Each agent has a context budget (16,000 tokens by default). A sliding window keeps recent turns, summarises older ones and sets prompt-cache breakpoints, and a budget report shows where tokens go. Prompts are versioned in the Prompt Store. The enterprise edition adds session compaction with a threshold and auto-compact.

Context budgetSliding windowPrompt StoreSession compaction
All 14 features →
Agent harnessAgent loopMemory & sessionsTool calling & MCPMulti-agent orchestrationHuman-in-the-loopGuardrailsEvals & test suitesRL environments & worldsModel routingAgent observabilityAGENTS.md & GitOpsBackground agents