Files

Teknium 5747590770 fix: follow-up improvements for salvaged PR #5456

- SQLite write queue: thread-local connection pooling instead of
  creating+closing a new connection per operation
- Prefetch threads: join previous batch before spawning new ones to
  prevent thread accumulation on rapid queue_prefetch() calls
- Shutdown: join prefetch threads before stopping write queue
- Add 73 tests covering _Client HTTP payloads, _WriteQueue crash
  recovery & connection reuse, _build_overlay deduplication,
  RetainDBMemoryProvider lifecycle/tools/prefetch/hooks, thread
  accumulation guard, and reasoning_level heuristic

2026-04-06 02:00:55 -07:00

__init__.py

fix: follow-up improvements for salvaged PR #5456

2026-04-06 02:00:55 -07:00

plugin.yaml

feat(memory): pluggable memory provider interface with profile isolation, review fixes, and honcho CLI restoration (#4623 )

2026-04-02 15:33:51 -07:00

README.md

feat(memory): pluggable memory provider interface with profile isolation, review fixes, and honcho CLI restoration (#4623 )

2026-04-02 15:33:51 -07:00

README.md

RetainDB Memory Provider

Cloud memory API with hybrid search (Vector + BM25 + Reranking) and 7 memory types.

Requirements

RetainDB account ($20/month) from retaindb.com
pip install requests

Setup

hermes memory setup    # select "retaindb"

Or manually:

hermes config set memory.provider retaindb
echo "RETAINDB_API_KEY=your-key" >> ~/.hermes/.env

Config

All config via environment variables in .env:

Env Var	Default	Description
`RETAINDB_API_KEY`	(required)	API key
`RETAINDB_BASE_URL`	`https://api.retaindb.com`	API endpoint
`RETAINDB_PROJECT`	auto (profile-scoped)	Project identifier

Tools

Tool	Description
`retaindb_profile`	User's stable profile
`retaindb_search`	Semantic search
`retaindb_context`	Task-relevant context
`retaindb_remember`	Store a fact with type + importance
`retaindb_forget`	Delete a memory by ID