Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.
Commits on main
fix(core): patch responses api parallel tool calling not returning tool call IDs (#6079)
081a1f6 Charles Packer committed 1 year ago
fix: various hardening to prevent stale state on background mode runs (#6072)
2e721dd Charles Packer committed 1 year ago
fix: v1 sdk tests directly subscripting from list endpoints (#6054)
a66a818 jnjpng committed 1 year ago
fix(core): sanitize messages to anthropic in the main path the same way (or similar) to how we do it in the token counter (#6044)
1802925 Charles Packer committed 1 year ago
fix: fix poison state from bad approval response (#5979)
363a5c1 Charles Packer committed 1 year ago
fix: re-add embedding dimension padding for archival memories (#6041)
a217c8f Kian Jones committed 1 year ago
feat: return new Model and EmbeddingModel objects for list model/embedding endpoints [LET-6090] (#6019)
501c325 jnjpng committed 1 year ago
fix(core): patch bugs on transcript formatting for sleeptime w/ HITL (#6025)
e8e94f2 Charles Packer committed 1 year ago
fix(core): fix `enable_sleeptime` on `letta_agent_v1` getting initial message sequence (#6018)
5beaa84 Charles Packer committed 1 year ago