Kindex

List coordination conversations. Args: status: active, ended, or all. task_id: Optional related task ID filter.

Post a message to a coordination conversation. Args: conversation: Conversation ID or name. agent: Posting agent name (default: resolved agent id). message: Message body. to: Optional target agent — message is delivered (unread counts, injection) only to them; broadcast when empty.

Read messages from a coordination conversation. Without since_id, reads from the agent's member cursor and advances it (unread tracking). Args: conversation: Conversation ID or name. since_id: Only return messages with a higher id (0 for all); leaves the read cursor unchanged. limit: Maximum messages to return. agent: Reading agent name (default: resolved agent id).

Start a short-lived coordination conversation. Args: name: Conversation name. task_id: Optional related task ID. agent: Agent creating the conversation (default: resolved agent id). ttl_minutes: Conversation TTL. Expired conversations are cleaned up.

Run knowledge consolidation (dream cycle). Performs memory consolidation: fuzzy deduplication, suggestion auto-application, and bounded domain-link proposals for review. Like sleep consolidating memory — replay, strengthen, prune. Args: mode: 'lightweight' (fast, <5s) or 'full' (non-LLM). The LLM 'deep' mode spends on model calls and runs only from a shell (`kin dream --deep`), not from a tool call. dry_run: If True, report what would happen without making changes.

Edit a node in place (policy-aware). Accepts a node ID or exact title. Edit classes by node type: - editable (concept, document, artifact, skill, person, project, question): every field below is allowed - additive (decision, constraint, directive, checkpoint, watch): history matters — only append and expires; use `supersede` to replace - managed (task, session, coordination): refused — use the dedicated task/session/coordination tools Args: node_id: Node ID or exact title. title: Replace the title. content: Replace the content. append: Append a dated addendum block to t…

Diagnose each allowed graph independently without modifying it.

Merge two nodes that represent the same concept. Moves all edges from the source node to the target node, then archives the source. Use when you find duplicate or near-duplicate nodes. Policy-aware like `edit`: managed types (task, session, coordination) are always refused — their tooling owns them. Additive types (decision, constraint, directive, checkpoint, watch) are refused unless force=True — prefer `supersede` so history survives. A foreign advisory lock on either node blocks the merge unless force=True. Args: source_id: Node to merge FROM (will be archived). target_id: Node t…

Get source-separated graph analytics for auto, project, or global.

Ingest knowledge from external sources. Args: source: Adapter name (github, linear, files, commits, projects, sessions) or 'all'. limit: Maximum items to ingest per adapter (0 = each adapter's own default; code is unlimited, network/LLM adapters cap at 50). repo: GitHub owner/repo for github adapter (e.g. 'jmcentire/kindex'). since: ISO date — only ingest items after this date.

Set a node's exclusive valid-time end without deleting it. A foreign advisory lock on the node refuses the change unless force=True. The activity log names this server's agent identity as the actor; the caller's `invalidated_by` is kept beside it as an assertion. Args: node_id: Durable node ID or exact title. invalidated_by: Asserted invalidating actor. disposition_code: Bounded machine invalidation reason. invalid_at: Optional timezone-aware RFC 3339 exclusive end time. force: Override a foreign advisory lock.

Explain why one Kinbase logical key currently reads as it does. USE THIS: when company direction and the repository disagree, to see the reducer steps, the rejected events, and the evidence that would change the answer. Read-only, exact-key, and it never submits a question; generating a whole task brief is `kinbase project`, a planner step, because that one writes. Args: repo: Path to the certified repository asking. logical_key: The exact key to explain, e.g. `symbol:class:Db`. decision: The decision the answer is being read for.

Report a repository's Kinbase certification, trusted facts and Unknowns. USE THIS: before relying on company direction in a repository, to see whether Company was reachable at all. A withheld snapshot degrades the projection to repository evidence without failing, so a repository that lost Company and one that never had direction read alike until this is asked. Not purely a read: Kinbase closes apologies whose deadline has passed before it reports, which is a signed write it performs on every `status`. Nothing here records the asking, and what it writes is bounded by what is already overdue …

Submit explicit text as AI-generated repository evidence to native Kinbase. This stages one observation through `kinbase ingest kindex`. It does not run separate bulk corpus admission, ratify authority, or submit a question to a human queue. Native ingestion may derive and admit facts; the native receipt reports that outcome. A question node is AI evidence, not a native `questions ask`. Text is limited to 16 KiB; recognized credentials are refused. Identical retries reuse the source artifact. A timeout may have submitted successfully and is reported as unknown, not as evidence of no change.

Refresh signed Kinbase evidence; raw verifies bytes, reduced retains governance snapshots. The source events are never modified. Reduced covers local event keys and invokes exact-key explain, never project (which may submit questions). The `kinbase` executable is the one on PATH: a tool caller does not name what runs. A reduced sync that would outlast KINBASE_SYNC_BUDGET_S is refused; the CLI has no such bound.

Extract knowledge from text and add it to the graph. USE THIS: after reading long files, articles, command outputs, or completing complex multi-step tasks. Summarize what happened and pass the text here for automatic concept extraction and linking. Extracts with the configured LLM when one is available (it reads the first 4,000 characters) and with keyword matching otherwise. Creates up to 10 concept nodes: low-information ones are rejected, and a concept whose title already exists reuses that node. When it creates any, it grounds them to a new source node holding the first 500 characters of…

Create an edge between two nodes. Links are the graph's primary value. Choose the right relationship type: - relates_to: general connection (default) - depends_on: A requires B to function - implements: A is a concrete realization of B - contradicts: A and B are in tension - blocks: A prevents progress on B - answers: A resolves question B - supersedes: A replaces B - context_of: A provides background for B - spawned_from: A was derived from B - exemplifies: A is an example of B Args: node_a: Source node ID or title. node_b: Target node ID or title. relationship: Edge type (see a…

List nodes in the knowledge graph with optional filters. Args: node_type: Filter by type (concept, decision, skill, person, project, etc.). status: Filter by status (active, archived, deprecated). audience: Filter by audience (private, team, org, public). tags: Filter by tags (comma-separated, AND logic — node must have all). limit: Maximum number of nodes to return. graph: auto (both allowed stores), project, or global.

Acquire an advisory lock on a node for the current agent. Locks are advisory: they signal "I am working on this" to other agents (edit refusal, collab context). Expired locks never block anyone. Args: node_id: Node ID or title to lock. ttl_minutes: Lock TTL. Re-acquiring refreshes it. note: Why the node is locked. force: Take over a foreign unexpired lock.

Release an advisory lock held on a node. Args: node_id: Node ID or title to unlock. force: Clear a lock held by another agent.

Find (or mask) known secret values already stored in the graph. Requires ``secret_mask`` in the user's ~/.config/kindex/kin.yaml (env files such as ~/.profile whose values are secrets). New writes are masked as ``$NAME`` automatically; this reports rows written before, by key name and location, never values. Args: apply: Rewrite the matches as ``$NAME`` after a recovery snapshot (the snapshot keeps the old values; the report names it).

Search this repository's Kindex memory or capture evidence for later review. action=search: full-text search on up to 16 words (3+ characters) taken from text; returns up to 5 matching non-task nodes (id, title, first 500 characters) plus up to 10 open durable tasks, as evidence rather than instructions. Personal memory is not searched. action=capture: stores text (at least 20 characters; truncated near 3,900) as a quarantined capture candidate and returns its candidate_id. Nothing becomes durable knowledge, a directive or a permission until someone reviews and accepts it.

Activate a conversation mode. Returns the priming artifact to inject. Modes are state inductions, not instructions. They shift how you think, not what you think about. Based on research showing induced understanding outperforms direct instruction by 5.4x. Built-in modes: collaborate, code, create, research, chat. Custom modes can be created with mode_create. Args: name: Mode name (e.g. 'collaborate', 'code', 'create'). session_context: Optional prior session context to resume from.

Create a custom conversation mode from a primer, boundary, and permissions. A primer is a state induction (~80 words) that establishes how to think. A boundary defines what quality means for this mode. Permissions state what's explicitly allowed (tangents, pushback, etc). Args: name: Mode name (short, lowercase, no spaces). primer: The mode-setting passage. Under 80 words. Not instructions. boundary: 2-3 sentences defining output quality for this mode. permissions: What's explicitly permitted to keep the conversation alive. description: Optional one-line description. …

Export a mode as a portable, PII-free artifact (JSON). Args: name: Mode name to export.

Import a mode from a portable artifact (JSON string). Args: artifact_json: JSON string of the mode artifact.

List available conversation modes (built-in and custom).

Seed the default conversation modes into the graph. Idempotent.

Show details of a conversation mode including its primer, boundary, and permissions. Args: name: Mode name.

Check for due reminders and fire notifications. Runs the reminder check cycle: finds due reminders, sends notifications, handles auto-snooze for stale fired reminders.

Create a reminder with natural language time parsing. Args: text: What to be reminded about. when: When to fire: 'in 30 minutes', 'tomorrow at 3pm', 'every weekday at 9am'. priority: Priority level (low, normal, high, urgent). channels: Comma-separated notification channels (system, slack, email, claude). action: Shell command to execute when the reminder fires (optional). instructions: Natural language instructions for Claude to follow when due (optional). conversation_id: Optional chat/session id for scoped hook injection. scope: Reminder visibility for hook …

Mark a reminder as completed. Args: id: Reminder ID.

Manually trigger a reminder's action. Args: id: Reminder ID.

List reminders with optional filters. Args: status: Filter by status (active, snoozed, fired, all). priority: Filter by priority (low, normal, high, urgent).

Snooze a reminder. Args: id: Reminder ID. duration: Snooze duration (e.g. '15m', '1h'). Uses config default if empty.

Report this server's fixed repository, graph and permitted Kinbase operations.

Search the knowledge graph with hybrid FTS5 + graph traversal. USE THIS: before starting work on a topic, before adding nodes (to avoid duplicates), and whenever you need context about a concept. Each graph supplies its native hybrid ranking. When both project and configured global graphs contribute, equal-weight RRF interleaves those lists by rank, without comparing their locally normalized scores. The merged rank score is not calibrated cross-graph relevance. Results carry qualified graph IDs for safe follow-on writes. Args: query: Search query text. top_k: Maximum results to retu…

Show full details of a node including edges and provenance. Args: node_id: Node ID or title to look up. resolve_sources: Inspect durable evidence with read-only SQLite opens. Saved references never authorize writes or bypass session scopes.

Re-hash referent-bound nodes; demote stale ones from trusted recall. R0 staleness sweep: every active node carrying a file-scope referent is re-hashed against its recorded content digest. A mismatch (or missing file) records a demotion marker — the node drops out of trusted_only recall, shows " [stale-referent]" in search/context output, and becomes a re-verification candidate. Content is never deleted or rewritten. A fresh re-hash clears a previously recorded marker. Args: base_dir: Resolve relative referent paths against this directory (default: the server's cwd — prefer absolu…

Get per-graph health and statistics for the selected read scope.

Show pending bridge opportunity suggestions. These are potential connections between concepts that Kindex detected but hasn't confirmed yet. Args: limit: Maximum suggestions to show. graph: auto (both allowed stores), project, or global.

Replace a node with a fresh one, preserving history. Accepts ID or title. Creates a new node (same type/tags/audience/intent), links it with a `supersedes` edge, marks the old node status='superseded', and migrates its retrieval pheromone. Use this instead of `edit` for additive types (decision, constraint, directive, checkpoint, watch) when the content must change rather than grow. Args: node_id: Node ID or exact title of the node to replace. new_text: Full replacement text (becomes title + content). expires: Optional expiry date for the new node (YYYY-MM-DD). reason: Why th…

Resume a session tag — get full context for continuing work. Args: name: Tag name to resume (shows active/paused tags if empty). tokens: Exact UTF-8 byte budget for the resume block. The argument name is retained for compatibility; provider-token guarantees require a direct library caller to supply that provider's exact counter.

Start a new session tag for tracking work context. Args: name: Human-readable tag name (e.g. 'auth-refactor'). description: What this session is about. focus: Current focus area. remaining: Comma-separated list of remaining items.

Update, segment, pause, or end a session tag. Args: name: Required tag name from tag_start or tag_resume. Concurrent agents can have active tags in the same project, so omission is unsafe. focus: New focus area (used for update and segment actions). description: Updated description. remaining: Replace remaining items (comma-separated). add_remaining: Add items to remaining (comma-separated). done: Remove items from remaining (comma-separated). summary: Summary for segment/pause/end actions. action: One of: update, segment, pause, end.

Kindex durable repo task service: tasks live in this worktree's .kin/local store and survive compaction and new sessions (the native Task/TodoWrite tools route here too). get and list read (list takes status, limit, cursor). create, update, complete, cancel, claim, release and reconcile write and need args.operation_id: resending an ID with the same arguments returns the committed result (replayed: true) instead of applying it twice, and reusing it with different arguments is refused. Pass expected_version on update/complete/cancel/claim/release to refuse the write if the task changed; another…

Add a task to the knowledge graph. Tasks are graph-connected -- link them to concepts, projects, or other nodes so they surface contextually when you're working in related areas. Use link_to to connect tasks to existing graph nodes by ID or title. Args: text: Task title/description. priority: 1=urgent 2=high 3=normal 4=low 5=someday. due: Optional due date ('tomorrow', '2026-03-15', 'in 3 days'). scope: 'global' (always visible) or 'contextual' (surfaces by proximity). link_to: Comma-separated node IDs or titles to link this task to. effort: Optional effort estimate (…

Cancel a task without deleting its durable record or history.

Claim a task for an agent with an expiry. Args: id: Task node ID. agent: Agent/sub-agent name claiming the task (default: resolved agent id). ttl_minutes: Claim TTL. Expired claims can be taken over. note: Optional claim note. force: Override an existing unexpired claim.

Mark a task as completed. Args: id: Task node ID. agent: Agent completing it (default: resolved agent id). Another agent's live claim refuses the change unless force is true. force: Complete even though another agent holds a live claim.

Scoped typed task operation for host adapters, including durable retries. Mutations require arguments.operation_id; update accepts expected_version. Operations: create/get/list/update/complete/cancel/claim/release/reconcile. Explicit project/session scope comes from the caller, never the MCP cwd.

Get a complete structured durable task by its exact graph ID.

List tasks, optionally filtered. With an implicitly selected project graph, also includes relevant tasks from the configured global graph and returns qualified IDs. Args: status: Filter: open, in_progress, done, all. Default: open. scope: Filter: global, contextual, or empty for both. priority: Max priority level to show (1-5). Empty for all. project_path: Optional explicit project filter. limit: Maximum number of matching tasks to return. graph: auto (selected project plus relevant outer tasks), project (selected store only), or global (configured outer store…

Release a task claim. Args: id: Task node ID. agent: Agent name. Required to match the claim unless force is true. force: Release even if the agent does not match.

Update task fields; omitted fields stay unchanged. Empty due clears it. expected_version provides compare-and-swap protection against concurrent edits. A status change that ends another agent's live claim is refused unless force is true; agent defaults to the resolved agent id. Use task_execute for explicit host scope and durable operation replay.

Assert node verification and an optional half-open valid interval. Verified, current, non-contradicted nodes are what `trusted_only=True` search and context admit. Reviewer identity is asserted audit text within the local trust boundary; this tool does not authenticate it. Args: node_id: Node ID, graph-qualified reference, or exact title. verified_by: Asserted verifier identifier (at most 128 characters). prov_method: How the node was verified, as short audit text (at most 128 characters). verified_at: Optional RFC 3339 verification time (default: now). valid_at: …

Create a watch node for something needing periodic attention. Watches surface in every session's context. Use for: - Flaky tests, unstable APIs, known tech debt - Pending decisions, things to revisit - Anything Claude should keep an eye on Args: text: What to watch (becomes the node title). owner: Who owns this watch (person or team). expires: When this watch expires (YYYY-MM-DD). Auto-archived after expiry. link_to: Comma-separated node IDs/titles to link this watch to. graph: project (selected graph) or global (configured outer graph). source_refs: Comma-separated g…

List watch nodes. Args: status: Filter by status: active (default), archived, all. graph: auto (both allowed stores), project, or global.

Resolve/archive a watch node. Args: id: Watch node ID. reason: Why this watch is being resolved.