v0.9.29
weave-os/routerv0.9.29Aug 16, 2026by rohitg00
Upgrading?
AI Summary
This release focuses on deepening agent capabilities with Cursor and Devin integrations, adding a DeepSeek connector, and improving memory provenance and graph extraction.
Key Highlights
- Cursor plugin integration with 7 auto-capture hooks and 17 skills
- Native support for Devin with 6 hooks and plugin manifest
- DeepSeek Harness connector (`connect dsh`)
- Write-time provenance stamped on every record
- Keyless graph extraction without needing an LLM key
New Features
- Cursor plugin with MCP, IDE, and CLI support
- Devin support with `connect devin --with-hooks`
- DeepSeek Harness connector
- New skills: `memory-discipline` and `/lesson`
- Write-time provenance on records
- Keyless graph extraction
- Viewer clarity pass with two-pane session explorer
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hardcoding `2024-11-05` (#908) - Hybrid BM25 + vector + graph ranking reaches `memory_recall`, not just smart-search - Superseded memory versions leave the search indexes; recall stops returning stale facts as current - Lesson recall runs off a real index instead of scanning the whole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
ollama/ollama★ 184,262
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
fatedier/frp★ 110,072
A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.
infiniflow/ragflow★ 92,647
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
gohugoio/hugo★ 90,197
The world’s fastest framework for building websites.
junegunn/fzf★ 83,717
:cherry_blossom: A command-line fuzzy finder