"sqlite" matching MCP servers:

An MCP server that coordinates Mistral API calls across multiple processes/clients using a shared SQLite queue, enforcing automatic rate limiting and priority-based queuing.

A local-first, multi-provider cost meter for LLM usage, exposed as MCP tools. Captures every call into a local SQLite ledger and lets any coding agent query spend, compare providers, and get recommendations — no cloud, no account. First-class support for Chinese providers (Qwen, DeepSeek) alongside Anthropic and OpenAI.

YourMemory is an MCP server that uses biological forgetting curves to automatically prune stale data and reinforce useful context for Claude agents. It beats Mem0 by 16% on benchmarks and runs fully locally with zero LLM overhead via spaCy and SQLite.

Persistent, local-first graph memory for AI coding agents. Provides durable cross-session memory via a local SQLite knowledge graph with typed relationships.

Persistent memory MCP server for AI agents, using SQLite with hybrid keyword and semantic search for long-term memory storage.

Enables scraping and comparing LLM inference pricing from multiple providers using Firecrawl, storing results in SQLite for analysis.

Exposes a local inference ledger over MCP stdio, letting agents query request counts, token usage, TTFT, energy consumption, local costs, cloud-equivalent costs, savings percentages, and per-model breakdowns from an OpenAI-compatible proxy's SQLite ledger. Provides four read-only tools so coding agents can answer questions about home GPU inference economics without opening a browser.

MCP server providing virtual memory for AI context with durable SQLite storage, retrieval, and bounded prompt assembly to manage context windows.

Enables durable, evidence-backed deliberation and Decision CI by running multi-stage model protocols with detached worker processes, persistent jobs, and SQLite-stored decisions, evidence, outcomes, and quality metrics.

A local-first MCP server that provides safe, governed read-only SQL access to SQLite and PostgreSQL, with validation, limits, task tracking, and report generation.

Seven-layer agent memory over MCP: zenbrain_store routes a general statement into a semantic fact, a narrated event into an episode, a sequence of instructions into a procedure, and zenbrain_recall tags every result with the layer it came from. zenbrain_consolidate runs one sleep-like maintenance pass; storage is a local SQLite file, with no account and no network call.

Open-source AI memory layer for LLM agents. Importance scoring, temporal decay, hierarchical memory (facts, summaries, themes), YMYL prioritization, and active retrieval with contradiction detection. Supports OpenAI, Anthropic, Ollama. Local-first with SQLite + FAISS.

Carbon-aware MCP scheduler that defers "do it later" / "by tomorrow" / "overnight" LLM tasks to the cleanest electricity-grid hour inside a deadline — 40-70% lower CO2 per task, 50% cheaper via Anthropic/OpenAI Batch APIs. 9 MCP tools, per-task carbon receipts to local SQLite, Apache-2.0.

Enables importing AI provider usage CSVs or syncing OpenRouter/OpenAI costs into a local SQLite ledger, then querying spend, budgets, and invoice-style summaries via MCP tools.

Enables quant research organizations to log hypotheses and outcomes, count trials for honest statistical verdicts, explore novel methods, run significance gates, and evolve reusable skills from validated trajectories, all backed by SQLite.

An MCP server that implements Andrej Karpathy's autoresearch pattern for iterative experimentation, offering a composable technique catalog, experiment scaffolding, and SQLite-backed tracking for AI-assisted optimization loops.

Enables Codex to offload bounded local analysis — repository and symbol discovery, context compression, code and diff review, test-log analysis, task triage, and second opinions — to local Ollama models over stdio MCP, with role, capability and quality gates returning uncertain work to Codex. It also records metadata to SQLite so a companion Windows tray/dashboard can show local usage.

Enables AI agents to query local video timelines by extracting speech, frame captions, and on-screen text into a SQLite store, exposing search and retrieval tools via MCP.

Gives AI agents governed, provenance-tagged memory where facts are invalidated rather than deleted and every recall result carries validity dates, confidence, and replacement links. Stores memory in a local SQLite file with tools for remembering, recalling, invalidating, and pinning facts, plus policy enforcement and an audit trail.

Persistent memory storage using SQLite for AI agents to store, search, update, and manage contextual memory via the Model Context Protocol.