Skip to content

feat: Add agent long-term memory with ondemand and always store modes#31

Merged
vinodvx merged 1 commit into
mainfrom
feat/memory
Jun 20, 2026
Merged

feat: Add agent long-term memory with ondemand and always store modes#31
vinodvx merged 1 commit into
mainfrom
feat/memory

Conversation

@vinodvx

@vinodvx vinodvx commented Jun 20, 2026

Copy link
Copy Markdown
Contributor

Description

  • Adds long-term memory to the agent SDK via agent.WithMemory, with recall before each run and store after (ondemand via save_memory or always via run-end extract).
  • Supports inmem, Weaviate, and pgvector backends with scoped recall/store in local and Temporal runtimes.
  • Wires memory into eval-harness and benchmarks through the existing YAML config (no extra files), plus an examples/agent_with_memory example.

Type of change

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to change)
  • Documentation update
  • Refactor / chore

Related issues

Closes #22

Checklist

  • [*] I have run make check
  • [*] I have run task examples:all
  • [*] I have run make tidy if I added or removed dependencies
  • [*] Commit messages follow conventional commits (e.g. feat:, fix:, docs:)
  • [*] I have added/updated tests for my changes
  • [*] Documentation is updated if needed

@vinodvx vinodvx merged commit 5d7186d into main Jun 20, 2026
4 checks passed
@vinodvx vinodvx deleted the feat/memory branch June 20, 2026 23:39
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Feature: Add native Long-Term Semantic / RAG Memory interface and providers

1 participant