continuityos
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CONTINUITYOS_DB_PATH | No | Path to the ContinuityOS SQLite database file. Corresponds to the --db argument in the MCP server command. | ~/.continuityos/memory.db |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| rememberA | Store a durable memory. Use for facts about the user, projects, rules, decisions you should recall later. |
| recallB | Hybrid recall (structural keyword + semantic vector) of the most relevant memories for a query. |
| upsertA | Create-or-update a memory by semantic KEY (idempotent). If (namespace,key) exists it is superseded (history kept) and replaced; else created. Use for stable values an agent overwrites over time: a config value, a current decision, a user preference. |
| findA | Exact key lookup: the CURRENT value stored under (namespace,key), or null. Deterministic point-read (not fuzzy recall) - reads back what upsert wrote. |
| contextB | Return a ready-to-inject context block of the most relevant memories for a query. |
| forgetB | Delete a memory by id. |
| list_namespacesA | List folder-like namespaces and how many memories each holds. |
| checkpointA | Close a session: record a delta, the next irreversible action, and a proof artifact path. |
| handoffA | Return a handoff pack (canon + frontiers + open loops + last checkpoint) to resume context in a new session/agent. |
| doctorC | Anti-drift check: cash/trunk frontier set, open loops bounded, checkpoint fresh, has proof. |
| set_frontierA | Set the trunk/cash/lab/parked focus (1 trunk + 1 cash + 1 lab discipline). |
| predictC | Digital-twin: likely stance on a situation, grounded in recorded rules and precedent. |
| alignmentB | Check a proposed action against canon/rules; flags conflicts with non-negotiable rules. |
| preflight_actionA | GOVERNANCE GATE: before running a tool/shell command, get a safety decision (ALLOW/WARN/HOLD/DENY/REQUIRE_CONFIRMATION/DRY_RUN_ONLY) with reasons + rollback plan. Call this BEFORE any dangerous action. |
| srd_statusC | Long-session safety: interaction count vs Safe Turn Depth. When reinject_due=true, re-inject the returned canon_reminder into context - omission-rules ('never do X') decay by ~turn 10 (Security-Recall Divergence). |
| memory_pointerA | Pass-by-reference: get a lightweight {namespace,key,version} pointer to a memory value instead of its content (A2A courier-tax fix). Dereference with recall/find. |
| memory_write_checkedA | Optimistic-concurrency write by key: succeeds only if current version equals expected_version, else returns a conflict. Prevents lost updates when multiple agents write the same key. |
| devils_advocateA | Challenge a claim or proposed action against your own memory + canon BEFORE acting: flags contradictions, superseded facts, missing evidence, canon conflicts, overconfidence, dishonest omissions, irreversible actions. Returns a verdict (STOP/RECONSIDER/PROCEED WITH CAUTION/PROCEED). Call before consequential moves. |
| system_auditA | Full-system audit: memory inventory + invariants (append-only integrity, bi-temporal ordering, canon presence, dangling supersede pointers). devil=true runs the devil's advocate over every failing finding. EU-AI-Act Article-12 style record. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 19 tools
Several tools overlap: remember/upsert/memory_write_checked all write memories; recall/context/find all retrieve; preflight_action/alignment/devils_advocate all check actions. The descriptions don't sufficiently clarify when to use one over another, leading to potential misselection.
Tool names mix single verbs (remember, find), nouns (context, alignment), compound verbs (set_frontier, preflight_action), and technical jargon (upsert, srd_status). There is no consistent verb_noun or other uniform pattern, making the set feel chaotic.
At 19 tools, the count sits in the heavier range. Many tools serve overlapping purposes and could be consolidated (e.g., recall/context, alignment/devils_advocate), suggesting slight over-scoping for the domain.
The core memory lifecycle is well covered: create (remember/upsert), read (recall/find/context), update (upsert), delete (forget). Session continuity tools (checkpoint/handoff) and safety checks add depth. Minor gaps like no direct ID lookup and no batch operations exist but are workable.