Stop re-exploring the same codebase
You give an agent a compact, persistent map of a recurring corpus. It begins oriented while still checking current evidence for each task.
Unit example (nearest native match)
See the idea in context
let analyst = agent_with_options(signature, json!({
"contextFields": ["codebase"],
"contextPolicy": {"preset": "adaptive", "budget": "balanced"},
"contextMap": {"maxChars": 1800, "infiniteEvolve": false, "evolveSteps": 1},
}))?.with_runtime(Box::new(QuickJsCodeRuntime::new()))?;- Load prior orientation
savedSnapshot carries useful structure learned on earlier successful runs.
- Keep the map compact
maxChars bounds what is injected into the agent context.
- Use it as a guide
The map points the agent toward evidence but never replaces current source.
Run itIn your own project
cargo add axllm
use axllm::{ai, ax};
use serde_json::json;
let llm = ai("openai", json!({"apiKey": std::env::var("OPENAI_API_KEY")?}))?;
let classify = ax("review:string -> sentiment:class \"positive, negative, neutral\"")?;Set OPENAI_APIKEY in your environment before running provider-backed code.
From a clone of the ax repo:
npm run example -- rust src/examples/rust/long-agents/codebase_peek_map.rsActive practice
Answer 2 in a row to learn this · attempt 1