vectorize-io/hindsight

Memory platform for AI Agents in 6 lines of code

Structural observability for AI conversations. Detects loops, stuck states, breakthroughs, and convergence patterns across 17 channels without analyzing content. MCP server + REST

Real-time cost observability for Model Context Protocol (MCP) tool calls. Wraps any MCP server, attributes spend per tool/project/customer. Free tier 25K calls/mo. EU-hosted

🧠 A high-performance PostgreSQL-backed MCP server acting as a super memory, task tracker, and dynamic database manager for AI agents. Features built-in connection pooling, a profe

MCP server that adds a fail-closed quality gate and hash-chained receipt ledger to any AI agent workflow.

MCP server for persona-driven AI sessions: practice interviews, conduct guided reflection, and role-play conversations with realistic personas

AI supply-chain security scanner and self-hosted control plane for agents, MCP, SBOM/SARIF, graph findings, runtime enforcement, and compliance evidence.

A local vector memory explorer with a modern UI. Browse, search, visualize and manage SQLite-vec databases from MCP Memory Service.

Pinecone Assistant MCP server

Vestige gives AI agents sharp memory: a local-first Rust MCP server that reaches backward through time to find the quiet change, decision, or service that caused today’s failure, n

Track your brand visibility across ChatGPT, Perplexity, Claude, and Gemini. Open source alternative to Otterly/AthenaHQ.

Grafana Loki MCP Repository

Official Vectorize MCP Server

MCP server for external memory layer for AI agents + more . Download from pypi , and get started

See through your agent's eyes. Visualize legacy code, architect new systems, understand everything.

Open-source observability and audit trail platform for AI agents. MCP-native, tamper-evident event logging, real-time dashboard.

Local-first MCP server + CLI giving terminal AI agents an endless, low-token memory via Anchored Compacting

Persistent memory system for AI coding assistants via MCP. Works with Claude Code, Cursor, Copilot, Windsurf, Cline.

Persistent memory for AI agents. Agents forget. CI remembers.

Persistent memory MCP server for Claude Code, Cursor, and GitHub Copilot. Long-term memory via Model Context Protocol with semantic search, Git sync, and team collaboration.

Production-grade persistent memory service for AI agents — FastAPI + pgvector + local ONNX embeddings

AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN

Tessera — Memory layer for every AI. 58 MCP tools, 54 REST endpoints, local-first, AES-256 encrypted.

Sistema de Memoria Dual con Búsqueda Integrada por Relevancia Expansiva (BIRE) — PostgreSQL + pgvector + Gemini Embeddings

Local-first MCP memory layer for AI coding assistants — persistent cross-session memory, stored entirely on your machine

Persistent memory for Claude Code — 41 neuroscience papers, 26 biological mechanisms with paper-bearing per-mechanism ablation evidence (E1 v3). LongMemEval R@10 98.4% / MRR 0.9124

Open-source cognitive engine for AI agents — persistent memory, a first-person journal, a four-layer ethics engine, and a per-user biological clock, over MCP. Apache-2.0.

The best-benchmarked open-source memory system for AI coding assistants

Competitive intelligence MCP server — monitor competitors and track how AI ranks your brand

📇 ☁️ 🍎 🪟 🐧 - Universal persistent memory for AI coding tools. Semantic code search, knowledge graphs, impact analysis, decision tracking, and 60+ MCP tools. Works across Cursor

UseCortex MCP Server — Give your AI coding agent a persistent memory. Read and write knowledge from any tool.

CLI + Local MCP - A shared structured memory store across Claude Code, Cursor, Windsurf, Antigravity, and every MCP client. Semantically queryable.

HyperStore-MCP

AKB — Agent Knowledgebase. Organizational memory for AI agents: vault-scoped docs / tables / files unified by URI graph, served over MCP.

Nucleus MCP server by Eidetic Works — persistent memory and governance for Claude, Cursor, Windsurf — file-based, no vendor lock-in.

Cross-platform agent logging and observability

Your AI agent finds the right files. Every time. Code graph context engine with 24 MCP tools — 170+ languages, triple search, +27% F1 improvement.

Transparent MCP proxy with OpenTelemetry tracing. Wrap any MCP server and persist traces to SQLite, Postgres or MySQL.

Encrypted, bidirectional local memory for your Claude Code Telegram bot — captures both sides at the plugin source, recalls via MCP.

Memory system for autonomous agents - built by an agent, for agents

MCP server that adds RAG-powered AI chat to any website. One command from Claude Code. Local vector store, multi-provider LLM (OpenAI/Anthropic/Gemini). Zero cloud dependency.

Persistent, correction-driven memory for AI agents. Cross-session, cross-platform (Claude Code, Codex, Gemini — any MCP client). Learns from mistakes, compresses context to save to

Precomputed reasoning cache for AI infrastructure decisions — 220K+ pages tracking the open-source AI ecosystem

A Model Context Protocol (MCP) server for GreptimeDB

MCP server: grounding/hallucination guard — verify a claim against evidence (Supported/Refuted/NEE) for AI agents

Regression testing for AI agents. Snapshot behavior,diff tool calls,catch regressions in CI. Works with LangGraph, CrewAI, OpenAI, Anthropic.

Semantic search MCP server for Claude Code conversations. Hybrid vector + keyword search across all your sessions, fully local.

Persistent semantic memory for AI agents — 100% local on Apple Silicon (MLX) or Linux/Ubuntu (CPU). Markdown source of truth, sqlite-vec + BM25 hybrid search, a codegraph-backed kn

🧠 A high-performance PostgreSQL-backed MCP server acting as a super memory, task tracker, and dynamic database manager for AI agents. Features built-in connection pooling, a profe

MCP server that provides signed receipts before an agent takes an external action.

Memory engine for AI agents — time axis (3-layer decay/promotion) + space axis (self-organizing topic tree). Hybrid search, LLM consolidation. Single Rust binary.

Kindly Debugger - Time-Travel Debugging for AI Workflows

Open-source team memory layer for AI coding agents — markdown files in git, user→team→org hierarchy, cross-vendor MCP server. Apache-2.0.

MCP server with persistent memory + FTS5 search for Claude Code conversation history. Index your ~/.claude/projects/, expose 10 MCP tools, browse via web UI. MIT-licensed.

Local-first production-readiness system for AI-built apps: read-only audit, evidence-based 0-100 score, guided fixes, learning plan, dashboard, CLI, and MCP.

Git-first memory for AI agents: Markdown files are truth, the index is disposable, writes are reviewable commits.

Persistent memory MCP server with typed memories, decay scoring, and token-aware context injection

[knowledge-rag] - Drop docs, search instantly from Claude Code — 12 MCP tools, 20 format parsers, hybrid search + reranking. Zero servers, zero API keys, 100% local.

An economical and fuel(token) efficient AI tool, graph session memory for looong chat session

Your agents forget. Neotoma makes them remember.

MCP-native AI SRE: ask what's broken in production, get a reviewed GitHub fix PR.

memstate-ai/memstate-mcp — indexed from awesome-mcp-servers-punkpeye

Engram-inspired memory MCP server with hot cache and pattern mining

🏎️ 🏠 🍎 🪟 🐧 - Zero-dependency MCP memory server. Single binary, 100% local, no Docker.

Persistent memory for AI coding agents

The most advanced Obsidian MCP — long-term memory for AI agents. Hybrid retrieval (BM25 + ML + BGE rerank, RRF-fused), HNSW live-update, agentic RAG (HyDE + sub-question), Obsidian

One memory. Every AI tool. Yours to keep. Local-first, MCP-compatible, Apache 2.0.

Generate a map of your codebaseto help AI Agents understand your architecture, coding conventions and patterns. Discoverable with Semantic Search

[](https://glama.ai/mcp/servers/perceptdot/percept) 📇 ☁️ 🏠 - AI-powered observability platform for agents. Auto-discovers and recommends MCP servers; built-in connectors for GA4,

Record and share your AI-driven product development journey

Local-first MCP memory & context-handoff server — capture context in one AI tool, resume it in another. Graceful decay, no cloud.

A detective for your data. Zero-config data quality monitoring — works with dbt, Postgres, BigQuery, Snowflake. No YAML.

Local-first memory layer for AI coding agents. Captures issues, attempts, decisions, and cross-project library gotchas — your AI starts experienced, not amnesiac. Native MCP server

Outcome-based persistent memory MCP server for Claude Code and OpenCode. Good advice promoted, bad advice demoted. pip install roampal.

Privacy-first developer intelligence — surfaces what matters from the noise

Self-hosted MCP server + dashboard giving Claude Code, Cursor & Hermes agents shared long-term memory over a git-backed markdown vault. Agent-native, Obsidian-compatible second bra

s60yucca/mnemos — indexed from awesome-mcp-servers-punkpeye

Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.

A memory engine for conversational AI agents, inspired by neuroscience and Buddhist psychology

ContextLattice is the local-first control plane for long-horizon agent memory and coordination.

Your AI forgets everything between sessions. Rekindle fixes that.

Zero context compaction for Claude Code & LLM agents. Persistent memory powered by OS primitives (demand paging, kswapd eviction, mlock pinning). Single SQLite file, MCP-native, mu

A debugging workflow plugin for AI coding agents. Turns terminal failures into source-backed fixes via MCP and structured skills.

Persistent memory for AI coding agents via MCP — a bitemporal knowledge graph of your codebase, served to Claude Code, Cursor, Gemini CLI, and any MCP client. Tree-sitter + Gemini

A Research Cortex. A research companion for Claude. Your library, notes & memory stay on your machine; answers cited from your own library; 30+ specialist skills; auto cross-pollin

Cognitive memory for AI agents. Pure Rust, <1ms recall, 2.7MB, zero cloud. Patent Pending.

Farnsworth SYNTEK — 7-layer recursive agent memory with context branching, holographic recall, and on-chain persistence.

A local-first cognitive substrate for neurodivergent professionals. Gives Claude memory, a sense of time, a translator for corporate ambiguity, and a guardrail that refuses to ampl

Self-hosted semantic memory over MCP for an engineering team's tacit knowledge. Rust, Postgres + pgvector.

MCP that brings persistent agent memory to Kiro, Claude Desktop, Cursor, and any MCP client — powered by agent-memory-daemon 🧠

🧠 Privacy-first MCP server for AI memory management. Save, search & organize chat history with intelligent summarization.

MCP server that audits RAG retrieval - logs what chunks the model saw before any answer was generated

Behavioral Verification Infrastructure — MCP-native intelligence layer for autonomous software correctness. 17 MCP tools, semantic workflow grouping, drift detection, counterfactua

Durable, local-first memory for AI coding agents over MCP — zero-dependency, curated & semantically de-duped, you own the data (SQLite + Markdown). Works with Claude Code, Codex &

Local, searchable project memory for AI coding agents. Markdown source of truth, MCP interface, safe structured updates — no cloud.

Self-learning memory for AI coding agents — MCP server