v0.9.29

imbhargav5/open-recorderv0.9.29Aug 16, 2026by rohitg00

Upgrading?

AI Summary

This release significantly expands the Cursor plugin with auto-capture hooks and MCP support, introduces new AI integrations for Devin and DeepSeek, and enhances memory discipline with provenance tracking and new skills.

Key Highlights

  • Major Cursor plugin expansion with 7 auto-capture hooks, MCP, and CLI
  • New support for Devin AI and DeepSeek Harness connector
  • Enhanced memory discipline with 'memory-discipline' and '/lesson' skills
  • Write-time provenance tracking for all records
  • Improved search ranking with hybrid BM25+vector+graph

New Features

  • Cursor plugin: 7 auto-capture hooks + 17 skills + MCP, IDE, and CLI
  • Devin support: `connect devin --with-hooks` and plugin manifest
  • DeepSeek Harness connector (`connect dsh`)
  • `connect pi` now installs the extension
  • New skills: `memory-discipline` and `/lesson` (corrections become confidence-weighted)
  • Write-time provenance on every record
  • Keyless graph extraction
  • Viewer clarity pass: two-pane session explorer, expandable records

Full Release Notes

No breaking changes, drop-in upgrade.

## Added
- Cursor plugin: 7 auto-capture hooks + 17 skills + MCP, IDE and `cursor-agent` CLI
- Devin support: `connect devin --with-hooks` (6 native hooks) and a Devin plugin manifest for `/agentmemory:<skill>` commands
- DeepSeek Harness connector (`connect dsh`), with `--with-hooks` for full auto-capture
- `connect pi` now actually installs the extension; capture reaches parity with the Claude Code plugin
- Two new skills, 15 → 17: `memory-discipline` (when to recall and save) and `/lesson` (corrections become confidence-weighted rules)
- Write-time provenance on every record: origin channel stamped at capture, save, and import
- Keyless graph extraction: the knowledge graph now populates without an LLM key
- `AGENTMEMORY_LLM_NOTHINK=1` to skip the hidden thinking pass during graph extraction
- Viewer clarity pass: two-pane session explorer, expandable records, honest zero states

## Fixed
- MCP `initialize` now negotiates the client's protocol version instead of hardcoding `2024-11-05` (#908)
- Hybrid BM25 + vector + graph ranking reaches `memory_recall`, not just smart-search
- Superseded memory versions leave the search indexes; recall stops returning stale facts as current
- Lesson recall runs off a real index instead of scanning the whole corpus per query
- `agentId` threads through every save path (#1159, #1160, #1197)
- Prompt dedup no longer swallows prompts after the first in a TTL window (#1173)
- Stop hook no longer summarizes twice (#1203)
- Per-session project attribution in the OpenCode plugin (#1188)
- Safe `agentmemory stop` in Docker mode (#1151)
- `~/.agentmemory/.env` now applies to every module at boot

## Changed
- Provider default models bumped to current generations (OpenAI, Anthropic, Gemini, MiniMax, OpenRouter); explicit `*_MODEL` overrides unaffected

**Full changelog**: https://github.com/rohitg00/agentmemory/compare/v0.9.28...v0.9.29

Related Repositories