clarilayer
Active·★ 76·NOASSERTION·Updated 2026-09-17
ClariLayer acts as a durable, reconciled context layer for individual analysts, enabling AI agents like Claude Code or Cursor to remember data definitions and corrections across sessions. It prevents agents from making the same data mistakes repeatedly by grounding definitions against real warehouse results.
#Context Management#AI Agent#Data Reconciliation#LLM Tooling#Semantic Layer#MCP Protocol#Data Definitions
01
Features
01Recall relevant context for AI agents.
02Remember and save durable data facts.
03Bootstrap context from existing data artifacts.
04Reconcile data definitions against real warehouse data.
05Propose and review agent-suggested facts.
02
Compatibility
Claude Code
AI Agent
Verified via docs
Cursor
AI Agent
Verified via docs
Codex
AI Agent
Verified via docs
claude.ai
AI Agent
Verified via docs
MCP Protocol
Integration
Verified via docs
Node.js
CLI Runtime
Verified via docs
03
Quick start
1
$ npx clarilayer init
04
Use cases
↳Prevent AI agents from repeating data mistakes across sessions.
↳Ground AI agent knowledge with reconciled data definitions.
↳Import and manage context from existing SQL, dbt models, and data dictionaries.
↳Manage and save engineering decisions, constraints, and incident lessons.
↳Enable human review and approval of agent-suggested facts and insights.
05
Alternatives
aictx★ 59
Repo-local continuity runtime for AI coding agents. Preserves work state, decisions, failures, validation evidence and repo context across sessions, helping agents behave less like cold-start rookies.
mcp-memory-server★ 27
Hosted memory for AI agents that learns and forgets — feedback reranks what helps, recall fades by recency. One key across Claude, Cursor, VS Code & ChatGPT. Official MCP Registry.
engram-mcp★ 18
MCP server in Rust for AI agent persistent memory: branch-aware session handoffs, local ONNX embeddings, SQLite-backed semantic search.
geml★ 29
One format, two readers. People and AI agents now co-write the same document. Legible for people; addressable, verifiable, and versioned for machines. GEML is plain text — organized by one typed block for everything, remembered by a .gemlhistory sidecar.
okf-agent-memory★ 843
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
projectmem★ 870
Local-first AI coding memory for AI agents. Records issues, attempts, fixes and decisions, then warns your agent before it repeats an approach that already failed. Native MCP server for Claude Code, Cursor, Antigravity and Codex. 100% local, no cloud, no telemetry. MIT.
aoci-code★ 1.8k
A persistent, Git-versioned map of your whole codebase and database schema that coding agents read before they touch anything. Local-first MCP server + CLI in Go: a governed repository index of code knowledge that gives Claude Code, Codex, Cursor, and opencode long-term context, memory, and code intelligence.
Comments
Log in to leave a comment
No comments yet. Be the first!