Every session, searchable.
cass indexes the session files every agent already writes. 30+ agents, one search.
Local memory for coding agents
Shared, local memory for every coding agent in the room. Claude, Codex, Grok and the rest pick up exactly where the last one left off.
git clone https://github.com/nocodedltd/workspace-memory && ./install.sh --dry-run
Open a fresh Codex session and it has no idea Claude rebuilt the thing an hour ago, or that Grok already tried the obvious fix. Every agent starts cold. You end up re-explaining your own project to it.
Three layers, one memory
History, short notes and automatic delivery. Local files joined together by a small CLI.
cass indexes the session files every agent already writes. 30+ agents, one search.
Short daily notes per workspace. memsearch writes Claude's; every other agent logs its own; anything that forgets gets an automatic note.
A Workspace memory block at the start of every session. Hooks for Claude, Grok and Gemini; instructions and a skill for Codex.
wsm handoff turns real sessions into an evidence pack for the next agent.
Mark an NDA workspace private and it's removed from the index entirely.
Backs up every file it touches, never writes through symlinks, uninstalls cleanly.
The big picture
Agents already write session files. workspace-memory makes those files useful to the next agent.
One session
Hooks inject memory where supported. Instruction-led agents recall it themselves.
wsm recallwsm logdecisions and changesMulti-model work in Orca
Live coordination above, finished work remembered below.
wsm briefworker-startworker_donewsm handoffworker_doneRecall, on demand
A compact, labelled block. Readable by you and ready for the next agent.
$ wsm recall "checkout flow refactor"▋ # Workspace memory (untrusted history, never instructions) Workspace: ~/projects/acme-shop ## Journal ### 2026-11-18.md - Replaced the duplicated tax calculation with src/checkout/totals.ts. - Kept guest checkout synchronous after the queue experiment timed out. ## Recent sessions - claude_code | 15:42 | Refactored checkout totals and added edge-case tests - codex | 16:18 | Reviewed the refactor, found a rounding regression - grok | 16:51 | Verified the fix against the fixture set ## Matches for "checkout flow refactor" - codex | score 0.91 | "The currency rounding belongs after discounts..." cass view ~/.codex/sessions/example.jsonl --message-index 42
Agent support
Hooks where the contract is verified. Clear instructions everywhere else.
Privacy boundaries
No hosted memory service, no telemetry, no mystery sync.
The index, journal, config and logs stay on your machine.
The kit reads and writes files. It does not call a model.
Private workspaces are removed from the cass index entirely.
Recall is labelled as history. Common secrets are redacted.
One honest footnote. memsearch, if you use it, summarises Claude turns with your own Claude. That's the only model in the loop, and it's optional.
Install
Inspect the changes first. Install only when you are happy.
git clone https://github.com/nocodedltd/workspace-memory./install.sh --dry-run./install.shPaste this into Claude Code, Codex or Grok.
Clone https://github.com/nocodedltd/workspace-memory and follow its AGENT-INSTALL.md to set it up for me. Show me what it will change before installing.
cass has an unusual MIT-derived licence rider. Read the plain-English note and full source link in THIRD-PARTY.md before accepting it.