Recall the right facts when needed You load task-relevant facts from a local catalog or external search only when needed. recall() makes the selected memories available on the next actor turn. go academy academy/topics/memory-recall website/content-src/academy/course.mjs academy Recall the right facts when needed
ax
Go github.com/ax-llm/ax/packages/go
TypeScript Python Java C++ Go Rust
Unit 7 · Give agents memory and orientation

Recall the right facts when needed

You load task-relevant facts from a local catalog or external search only when needed. recall() makes the selected memories available on the next actor turn.

recall()8 focused minutesNot started
Worked example

See the idea in context

assistant := axllm.NewAgent(signature, map[string]axllm.Value{
    "memoriesCatalog": memories,
    "skillsCatalog": skills,
})
Run itIn your own project
go get github.com/ax-llm/ax/packages/go

import axllm "github.com/ax-llm/ax/packages/go"

client := axllm.NewAI("openai", map[string]axllm.Value{"apiKey": os.Getenv("OPENAI_API_KEY")})
classify := axllm.NewAx("review:string -> sentiment:class \"positive, negative, neutral\"", nil)

Set OPENAI_APIKEY in your environment before running provider-backed code.

In the ax repo

From a clone of the ax repo:

npm run example -- go src/examples/go/long-agents/codebase_peek_map.go
Active practice

Show that you can use it

Answer 2 in a row to learn this · attempt 1
Keep exploring

Source-backed follow-up