v0.9.29

mukul975/cve-mcp-serverv0.9.29Aug 16, 2026by rohitg00

Upgrading?

AI Summary

This release adds significant support for Cursor and DeepSeek, introduces new skills, enables keyless graph extraction, and fixes MCP initialization and memory recall bugs.

Key Highlights

  • Added Cursor plugin with hooks, skills, and MCP support
  • Added DeepSeek Harness connector
  • Enabled keyless graph extraction
  • New skills: `memory-discipline` and `/lesson`
  • Write-time provenance on every record

New Features

  • Cursor plugin
  • DeepSeek connector
  • Keyless graph extraction
  • New skills
  • Write-time provenance

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- Superseded memory versions leave the search indexes; recall stops returning stale facts as current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