Context Engine - AI Agent Context Management

Context Engine - AI Agent Context Management

Context Engine provides production-grade patterns for managing what AI agents know, remember, and retrieve. It covers the full lifecycle: ingestion of project knowledge, optimal packing of context windows, persistent memory across sessions, and retrieval-augmented generation for large codebases. The difference between a useful agent and a hallucinating one is context management.

Core Capabilities

• Context window architecture — token budget allocation plus greedy, tiered, and adaptive-compression packing strategies.
• Memory architecture — three-layer model (working / session / knowledge base), promotion protocol, and staleness detection.
• Code retrieval — file-level, chunk-level (RAG), and dependency-aware retrieval with code chunking and embedding guidance.
• Knowledge graph construction — codebase graph schema (nodes + edges) and graph queries that resolve agent questions.
• Window optimization patterns — sliding window with anchors, progressive summarization, selective tool-result caching.
• Memory tool & context editing — file-backed persistent memory across sessions, plus context compaction (evict stale tool outputs, summarize-and-replace history) to keep a long loop from exhausting the window.
• Long-context strategies — when to use a 1M-token window vs. RAG vs. a hybrid agent loop, budget allocation across a big window, and position/attention effects.
• Multi-agent context sharing — shared context bus and a five-element handoff protocol.

When to Use

• Bootstrapping agent context for a new codebase (index → graph → summary → tiers).
• Optimizing context for a specific task (bug fix, feature, refactor, review).
• Capturing, promoting, and pruning session memory across sessions.
• Designing a RAG pipeline for code retrieval.
• Coordinating context across multiple collaborating agents.

Clarify First

Before designing or analyzing, confirm these inputs. If any is unknown or vague, ASK — do not assume:

• Which task — bootstrap context for a codebase, optimize for a specific task, design persistent memory, or build a code RAG (selects the analyzer/pruner/indexer and the playbook)
• Token budget — the context-window ceiling (sets --budget and which packing strategy applies)
• Source content — the files/codebase or knowledge base to index (the input the scripts process)

Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.

Tools