A persistent knowledge graph for AI-assisted workflows. Your AI never starts a session blind.
Memory plugins capture what happened. Kindex captures what it means and how it connects.
A weighted knowledge graph that grows intelligence over time — understanding relationships, surfacing constraints, and managing context injection.
Not a log file. Nodes with types, weights, domains. Edges with provenance and decay. The graph understands what matters.
From 100 to 4000 tokens. Auto-selects the right depth based on your available token budget. Never eats your context window.
Constraints block deploys. Directives encode preferences. Watches flag attention items. Checkpoints run pre-flight.
.kin inheritance chains from service to platform to org. Private/team/org/public scoping with PII stripping on export.
Hybrid FTS5 + graph traversal. 192 nodes, 11,802 edges searched in 142ms. Built on SQLite for zero-config speed.
Auto-capture knowledge on commits. Git hooks install with one command. Your codebase history becomes searchable context.
Three-tier prompt architecture with Anthropic prompt caching. Stable knowledge cached at 10% cost. Only the question pays full price.
Named work context handles that replace resume files. Track focus, remaining items, and topic segments. Resume seamlessly in new sessions.
Actionable work items linked to graph concepts. Tasks surface contextually via graph proximity. Priority, status, and completion tracking built in.
Time-based triggers with shell commands or Claude instructions. Natural language scheduling. Snooze, execute, or complete. Fires at session start.
Ongoing attention flags for flaky tests, unstable APIs, tech debt. Set owner and expiry. Watches surface in every session's context automatically.
Research-backed priming artifacts that induce processing modes in AI sessions. Five built-in modes. Create custom modes from sessions and export for team sharing.
signet-eval gates every tool call with deterministic policy enforcement. Define rules for what your AI can and can't do with your knowledge.
signet-eval evaluates in ~2µs. Zero runtime overhead.
Learn more at signet.toolsWhen other plugins dump everything into context, Kindex auto-selects the right depth. 200 tokens of executive summary or 4,000 tokens of deep context — whatever fits.
Your plugin doesn't eat the context window. It adapts to it.
From novel writing to multi-service architectures, Kindex scales to your knowledge.
Ingested a 162-file fantasy novel vault — characters, locations, magic systems, plot outlines — in one pass. Cross-referenced by content mentions. Searched in milliseconds.
Link knowledge across repositories with .kin inheritance chains. A service repo inherits from platform context, which inherits from org-wide standards. Every Claude session knows the full stack.
Track research papers, API documentation, competitive analysis. Kindex maintains weighted connections between concepts so you can ask questions that span your entire knowledge base.
Kindex isn't just for you. Every agent in the Exemplar stack queries the same knowledge graph.
Fixer agents query Kindex for prior incident patterns before attempting remediation
Code generation agents query for architectural decisions and constraints
Records operational events as queryable knowledge that enriches future sessions
Choose your preferred integration. Zero configuration required.
Two commands. Zero configuration. Claude Code gets 37 native tools instantly.
Comprehensive control over your knowledge graph, from both AI-assisted and manual workflows.
Find relevant knowledge by query (filter by --tags)
Add knowledge with type, weight, and tags
Get tiered context for current session
Display a specific node's full details
Ask questions across your knowledge graph
Extract and store knowledge from text
Create typed edges between nodes
Browse nodes with filters (type, status, tags, audience)
Graph overview and health
AI-powered suggestions for what to capture
Density, components, degree distribution
Diagnose graph health: orphans, bridges, fading nodes
Merge duplicate nodes, moving edges and archiving source
What changed, by whom, when
Ingest from GitHub, git, files, sessions, code (ctags/cscope/tree-sitter)
Start a named session tag for work context
Update, segment, pause, or end a session tag
Resume a session with full context injection
Create actionable work items linked to concepts
List and filter tasks by status and priority
Mark tasks completed with optional summary
Create time-based reminders with natural language parsing
List all active reminders
Defer a reminder to a later time
Mark a reminder as completed
Run the reminder check cycle for due items
Manually trigger a reminder's action
Activate a conversation mode -- returns priming artifact
List available modes (built-in and custom)
Show mode details: primer, boundary, permissions
Create a custom mode from primer/boundary/permissions
Export a mode as PII-free portable artifact
Import a mode from a portable artifact
Seed the five default conversation modes
Flag items needing ongoing attention (flaky tests, tech debt)
List active watches with status
Archive a watch when the issue is resolved
Zero-config storage with FTS5 full-text search. Your knowledge lives in a single portable file at ~/.kindex.
Nodes carry type, weight (0.0-1.0), domain tags, and audience scope. Edges track provenance and naturally decay, keeping your graph fresh.
Hybrid BFS + FTS5 traversal assembles context from graph relationships. Five tiers auto-select based on available token budget for optimal context injection.
Codebook (stable node index) and query-relevant context are cached via Anthropic prompt caching at 10% cost. Graph edges predict which nodes to pre-cache per topic.
Install in under a minute. Free, open source, MIT licensed. Your knowledge stays local.