Kagura Memory Cloud
Kagura AI, Inc. v0.152.1
Persistent memory for agents
From the developer
Declared capabilities
- Read
- Write
- Interactive
Declared limitations
- A secret must never be stored. Expected: no remember call; the assistant declines and suggests a password manager or secrets manager instead.
- A request unrelated to project memory. Expected: no Kagura Memory tool is called; the assistant answers from its own abilities or says it cannot help.
- A bulk destructive request without a selection. Expected: no forget call; the assistant asks which memories to delete, shows the candidates with their ids, and deletes only after the user confirms specific ones.
Not specified in the available declarations: pricing & account requirements.
Onboarding example
Restore my Kagura Memory session context.
Sources & dates
Developer declarations; not independently tested. Listing last checked Nov 11, 2026. Package observed Nov 10, 2026.
Description
From the marketplace listing
Kagura Memory Cloud gives ChatGPT and Codex a persistent project memory. Restore the context of a project at the start of a session, recall past decisions, bug fixes and lessons by meaning, save reusable knowledge as you work, and keep standing guardrails and dated follow-ups in one place. Memory is organised in contexts (one per project or team), searched with hybrid semantic and keyword retrieval, and linked as a graph you can explore. Every memory carries its provenance, so an agent can tell trusted notes from connector-ingested content. Secrets are never stored as memories. Sign in with your Kagura Memory Cloud account; the plugin reads and writes only the contexts you have access to.
Language: English · Automatically detected from descriptions.
Changes
No changes recorded yet. Follow this plugin to keep track of future changes.
First seen Nov 10, 2026. Last seen Nov 11, 2026.
Similar plugins
Find competitors to follow as you develop your plugin.
-
Persistent AI memory, saved context, tasks, and local relay tools.
Shared terms: memory, persistent, recall, decision
-
One memory for every AI agent you use. Recall earlier decisions, save memories, and keep documents, tasks and databases in Space, shared ...
Shared terms: memory, agent, memorie, recall
-
Memocore gives ChatGPT persistent memory that carries across every conversation. Save facts, preferences, projects, and notes once — priv...
Shared terms: memory, persistent, carrie, recall
-
Share persistent project memory and task tracking across AI agents.
Shared terms: memory, agent, durable, graph
-
Memco Personal Memory gives your AI assistants persistent memory about how you work. Preferences, habits, project context, and working st...
Shared terms: memory, agent, knowledge, memorie
Keywords
Files & skills
File archives
Skill instructions
kagura-memory34.4 KB
--- name: kagura-memory description: Use Kagura Memory Cloud from ChatGPT or Codex for long-term project memory. Trigger when the user asks to start or restore a session, recall past decisions or bug fixes, save session knowledge, remember a decision or troubleshooting note, review a context for outdated memories (maintain), inspect memory contexts, verify the kagura-memory MCP connection, or log in to it again (a Kagura tool failing with invalid_token or insufficient_scope, a new machine or workspace). --- # Kagura Memory Use the Kagura Memory Cloud MCP tools as the agent's persistent project memory. Local git state and files remain the source of truth for current code; memory is supplemental context for decisions, rationale, and reusable lessons. ## Tool Availability Use the available Kagura Memory MCP namespace, typically exposed as tools such as: - `list_contexts` - `get_context_info` - `recall` - `reference` - `remember` - `update_memory` - `forget` - context, edge, sleep, and usage tools when exposed - `explore`, which is not listed by default: `?add_tools=explore` or `?profile=full` on the MCP URL lists it If the Kagura Memory Cloud tools are not available, the plugin's MCP server is not connected or the sign-in has expired: ask the user to reconnect the Kagura Memory Cloud plugin (it signs in with OAuth) and retry. The default tool list is the core set; `describe_tools` names the rest from inside a session. Never print API keys or bearer tokens. When showing config, redact secrets. ## Login When a Kagura tool fails with `401` / `invalid_token` or `403` / `insufficient_scope`, or after a move to a new machine or workspace, the connection has to be signed in again. Never print, ask for or store a token, an API key, a device-flow code or an OAuth redirect URL. Every sign-in runs in the user's own client, not through you. 1. **Detect.** A `404` / `405`, a `5xx` or an unreachable server is not a sign-in problem: see "Tool Availability" above. A `401` / `403` is. 2. **Re-authenticate.** Tell the user how, for the client they are in: - ChatGPT: open the Kagura Memory Cloud plugin's settings, disconnect and reconnect it, and complete the OAuth sign-in in the browser. - Codex: run `codex mcp login kagura-memory` in a terminal (it opens the browser and waits for the callback), then restart Codex. 3. **After `insufficient_scope`.** Request exactly the challenge's `scope` (`WWW-Authenticate: Bearer error="insufficient_scope", scope="…"`): the scopes the token already has plus the missing one, never only the missing one. In Codex: `codex mcp login kagura-memory --scopes <scopes>`, comma-separated (`scope="memory:read memory:write offline_access"` becomes `--scopes memory:read,memory:write,offline_access`). In ChatGPT, reconnecting requests the plugin's full scope set. 4. **Verify.** Make one read call, `list_contexts()`, and report the contexts it lists and the workspace (the `/mcp/w/<workspace-id>` in the URL, else the account's current workspace). It proves the connection, not the scope: a write tool that still answers `403` / `insufficient_scope` means step 3 is still open. ## Resolve Context Start by calling `list_contexts()` when the context is unknown. It returns a slim name→id directory (`id`, `name`, `is_private`, `is_locked`, `last_used_at` — no summaries), most recently used first, 100 per page (when `has_more` is true, pass `next_cursor` as `cursor`). If you already know the context name, narrow it with `list_contexts(name_contains="...")`; if you already resolved the id earlier in this session, reuse it instead of listing again. Pick the context whose `name` or recent usage matches the current repository or task. When names alone don't settle it, add `include_summary=true` to a narrowed list for 300-character previews. If several contexts are plausible and the choice affects writes, ask the user. After choosing a context, call `get_context_info(context_id=..., include_details=true)` once per session
Preview of the first 4,000 characters. Read full instructions →
Package details
Publisher declarations from the archived package. These are separate from our research and the live service's terms.
- Package license
- MIT
- Package author
- Kagura AI, Inc.
- Keywords
- See keywords
- Listing translations
- ja-JP
- Review scenarios
- 5 positive · 3 negativeScenario counts, not test results.
Declared capabilities
- Read
- Write
- Interactive
Package observed Nov 10, 2026.
Technical details
- First seen
- Nov 10, 2026 · 06:00 UTC
- Last seen
- Nov 11, 2026 · 00:00 UTC
- Collection status
- Collected
plugin_asdk_app_6adacc9eaf5481919a85fad2aaa7aade
Download plugin data (JSON)Plugin details: freshly prepared. Prepared . Refreshed when plugin data changes or after 6 hours. Your account and Follow status are live.