Definition
What is Context Compression?
Last updated
The practice of reducing token count in an AI agent's context window while preserving the information needed to complete tasks.
As AI agents work through multi-step tasks, they accumulate conversation history, tool outputs, and observations that dilute attention. Context compression techniques like structured summarization, tool response offloading, and embedding-based reduction keep the working context focused. Research shows effective compression can reduce memory usage by 26-54% while preserving task performance.
Further reading
Articles about Context Compression
Pruning context made agents more accurate, not just cheaper
Pruning an agent's tool history raised task completion from 71% to 91.6%. What the summary rescued was not content but the agent's place in its own work.
Context window blindness: agents can't see their limits
Context window blindness: four frontier models misjudged their own context size by 43 to 84%. Why compaction drops the wrong things, and what fixes it.
Kimi K3's 1M context runs mostly on linear attention
Kimi K3's 1M-token window runs on Kimi Delta Attention: hybrid linear attention with a fixed-size state. Why cheap long context still needs context curation.
How agents manage their own context window
Agent context management is shifting from fixed harness rules to learned, runtime decisions an agent makes about its own window. What the 2026 research shows.
All terms
View full glossaryPut context into practice
Create your first context container and connect it to your AI tools in minutes.
Create Your First Container