MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
decay-memorygithub.com/trssantos/decay-memoryupdated this year
Memory that forgets. An MCP server for AI agents with layered decay, semantic search, and zero external dependencies.
MIT -
agentic-timegithub.com/agentralabs/agentic-timeupdated this year
Temporal reasoning for AI agents — deadlines, schedules, sequences, duration estimation (PERT), and decay models. One .atime file. Rust core + MCP server.
pypi MIT ★ 4 -
mcp-memorygithub.com/ShipItAndPray/mcp-memoryupdated this year
Smart memory for AI agents. Solves the Karpathy problem: memories decay, topics are frequency-weighted, one-time questions don't become obsessions. 7 tools. Zero deps.
MIT ★ 2 -
PostgreSQL-backed MCP memory server with thermal decay + knowledge graph + hybrid retrieval
MIT -
A personal knowledge graph: extraction, a verification ladder, retrieval, and decay — served over MCP to any client
cargo MIT -
A claims memory for agents: assert beliefs, let them decay, surface contradictions (MCP + CLI)
npm MIT -
Persistent memory graph for AI coding agents — semantic search, knowledge graph, and time-based decay over MCP
pypi MIT ★ 5 -
Git-style version control for multi-agent shared memory — Provenance Firewall, confidence decay, and cascading rollback (MCP-compatible).
MIT ★ 1 -
mnemo-mcpgithub.com/Skye-flyhigh/mnemo-mcpupdated this year
A portable cognitive memory for AI agents. An MCP server with semantic search and decay.
npm MIT ★ 2 -
Open agent-reputation infrastructure on Solana: bonded attestations, decayed scores, MCP tools, and a gaming-resistance benchmark
MIT -
hyphaegithub.com/basidiocarp/hyphaeupdated this year
Persistent memory and RAG for AI coding agents. Episodic memories with decay + durable concept graphs. MCP server + CLI. Rust.
MIT ★ 2 -
claude-memory-mcpgithub.com/FirmengruppeViola/claude-memory-mcpupdated this year
Persistent long-term memory for Claude Code via MCP. Auto-captures conversations, semantic search, importance scoring, decay. Just works.
npm NOASSERTION ★ 6 -
Memory that knows what to forget. An MCP server giving AI agents curated long-term memory: half-life decay, reinforcement on recall, and pruning.
MIT -
Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.
pypi NOASSERTION ★ 274 -
engramgithub.com/199-biotechnologies/engramupdated this year
MCP server for AI memory -- hybrid search (BM25 + semantic + knowledge graph), temporal decay, local-first
npm MIT ★ 10 -
mindmap-mcp-servergithub.com/ravi-labs/mindmap-mcp-serverupdated this year
Local-first MCP memory & context-handoff server — capture context in one AI tool, resume it in another. Graceful decay, no cloud.
npm Apache-2.0 ★ 6 -
local-memorygithub.com/RanchoCooper/local-memoryupdated this year
LocalMemory is a local-first memory layer for AI agents with semantic search, memory decay, and association linking, integrable with Claude Code via the MCP protocol.
MIT -
mcp-server-gsc-progithub.com/ricardo-nth/mcp-server-gscupdated this year
Enhanced MCP server for Google Search Console — fresh data, hourly analytics, search type filtering, content decay detection, keyword cannibalization, and more
npm MIT -
Forgetting engine for AI agents — memory TTL, decay, eviction, audit. The opposite of memory programming.
npm MIT -
Living memory system for AI assistants — SQLite + MCP with decay, learning, and knowledge graph
npm MIT ★ 1 -
@saluca/asphodelgithub.com/salucallc/asphodelupdated this year
Local-first agent memory — topic index, FTS, hybrid vector search (BM25 + embeddings + RRF), temporal decay, importance/ttl/persona scoping, bundled MCP server
npm Apache-2.0 -
Mnestra — persistent developer memory MCP server for Claude Code, Cursor, Windsurf. Hybrid search, cross-project memory, tiered recency decay. The LLM is stateless, Mnestra isn't.
npm MIT -
Structural long-term memory for DeepSeek Harness: supersede/decay/entity-state store, 15 MCP memory tools, automatic recall, bounded context band
npm MIT ★ 3 -
engram-rsgithub.com/kael-bit/engram-rsupdated this year
Memory engine for AI agents — time axis (3-layer decay/promotion) + space axis (self-organizing topic tree). Hybrid search, LLM consolidation. Single Rust binary.
npm MIT ★ 28 -
apigithub.com/smara-io/apiupdated this year
Memory API for AI agents — semantic search, Ebbinghaus decay scoring, knowledge graphs, MCP native. Drop-in mem0/Zep alternative. $19/mo vs $249+.
MIT -
Persistent memory database for MCP systems — SQLite, FTS5 search, vector embeddings, 3-signal RRF recall, ACT-R decay, graph edges. (Companion repo — architecture and interface only. Source lives in the private engine.)
-
Local-first personal knowledge base with decay-based recall. Ingests markdown, code context, and AI tool events into structured memory with time-aware ranking.
MIT ★ 1 -
agent-memorygithub.com/tahasiddiquii/agent-memoryupdated this year
A long-term memory service for agents: scoped episodic and semantic memory ranked by relevance, recency, and importance together, with consolidation, decay/forgetting, and an MCP server. Offline, keyless, recall- and isolation-gated.
-
Notes die in folders. Stellavault keeps your knowledge alive — 3D knowledge graph, AI semantic search, memory decay tracking, P2P federation, 17+ MCP tools. npm i -g stellavault
npm MIT ★ 7 -
UltraMemorygithub.com/win4r/UltraMemoryupdated this year
Universal AI Agent Long-Term Memory Engine — Hybrid Vector+BM25, cross-encoder reranking, Weibull decay, LLM smart extraction, semantic dedup, tiered content. Zero-ops LanceDB backend.
★ 7 -
Cognitive architecture for persistent AI agent memory. Knowledge graph with learning retrieval, ACT-R decay, and spreading activation. Markdown-native, local-first, zero cloud. MCP server + CLI.
npm Apache-2.0 -
anamnegithub.com/venumittapalli576/anamneupdated this year
Brain-inspired local-first memory layer for Claude, Cursor, and any MCP-compatible AI tool. Three memory layers (episodic / scratchpad / working), ACT-R activation decay, 21 MCP tools. Local SQLite + ChromaDB, no SaaS.
MIT -
Self-improving skill memory for coding agents: learn, recall, reinforce, decay — with provenance on every memory and trust only you grant. Local SQLite, no API key, no cloud.
pypi Apache-2.0 ★ 11 -
agentmem-vectlitegithub.com/mcsedition-hub/agentmem-vectliteupdated this year
Persistent memory for AI agents — powered by VectLite. Hybrid search, context compaction, multi-agent swarm, memory teleportation, MCP server, skill engine, decay & conflict resolution, and worktree-aware branch-scoped memory.
★ 4 -
Cognitive memory database for AI agents — consolidates duplicates, detects contradictions, and fades stale memories via temporal decay, written in Rust (Apache-2.0) as a library, MCP server, or HTTP cluster.
cargo Apache-2.0 ★ 180 -
Reputation-based marketplace where autonomous AI agents discover services, negotiate deals via LangGraph (LLM or strategy engine), and build time-decaying reputation. FastAPI + WebSocket dashboard, A2A & MCP servers, game-theory analytics.
MIT -
Self-hosted, human-like memory for AI agents: per-type decay, auto-linked associations, nightly consolidation, compressed vector search, and a web UI with login. Rust + Qdrant, REST and MCP.
MIT ★ 19 -
Long-term memory engine for coding agents: two-stage retrieval + gating, hybrid BM25+vector, Ebbinghaus decay, single SQLite file, MCP-ready. Dogfooded daily: 3,300+ memories across 4.5 months.
MIT ★ 6 -
Native Model Context Protocol (MCP) server fusing Meta ambient multimodal perception with Muse continuous episodic memory streams and Ebbinghaus recency decay.
MIT ★ 1 -
Model Context Protocol (MCP) server for room acoustics engineering: Room modes (Axial, Tangential, Oblique), Bonello & Bolt criteria compliance, Schroeder cutoff frequency, Sabine & Norris-Eyring RT60 reverberation decay, and speaker/sweet-spot placement.
npm MIT -
Hierarchical knowledge base for AI. An MCP server that indexes your documents into a trigger-navigable node/chunk graph with hybrid retrieval — a permanent vault, no decay. Runs standalone or behind the Gray Matter gateway.
NOASSERTION -
Read-only lookups against your own OpenCTI instance (CLI + MCP) — IOCs through observables and indicators with sightings and decay, threat actors and techniques by name, alias or ATT&CK id, their relationships, reports and attachments. Verified against OpenCTI 6.7.4
MIT -
SQLite of agent memory — single-file, embeddable, zero-config. Episodic + semantic memory, hybrid BM25+vector recall, bitemporal facts, spreading-activation, working memory, async API, LLM compression, Ebbinghaus decay, GDPR forget, multi-agent, MCP-native.
Apache-2.0 ★ 4 -
Persistent cognitive memory for AI agents — drop-in MCP server for Claude Code, Cursor, and Windsurf with temporal decay, contradiction detection, a knowledge graph, and autonomous consolidation, backed by the YantrikDB Rust engine.
pypi MIT ★ 25 -
Memory-augmented AI platform with a knowledge graph, temporal decay, versioned rollback, semantic drift tracking, and cryptographically signed cross-agent memory federation with OpenMemory MCP integration for Cursor, Claude Desktop, and ChatGPT.
★ 1 -
Memory backbone for AI agents. Four-tier store — working, episodic, semantic, procedural — with decay, consolidation, and association graphs. Fused semantic + SIMD-accelerated hybrid recall, in-process MCP, REST/gRPC, and language SDKs.
npm Apache-2.0 ★ 28 -
Google Search Console MCP server for Claude, Claude Code and Cursor: queries, pages, performance and 9 ready-made SEO reports (striking distance, content decay, cannibalization, low CTR). No Google Cloud project needed.
MIT -
concord-plugingithub.com/zkwasm/concord-pluginupdated this year
Concord — multi-agent collaboration rooms for AI agents. Claude Code plugin + MCP server (also Gemini/Codex/Cursor). End-to-end encryption + server-enforced coordination primitives (signal decay, quorum vote, claim lease).
npm MIT ★ 2 -
Git DAG indexing, AST symbol graphs, and hybrid semantic code search MCP server for AI coding agents (Claude Code, Cursor, Windsurf). Maps repositories into PostgreSQL + pgvector with recursive caller/callee dependency graphs and temporal recency decay.
MIT -
Brain-like persistent memory for AI agents. Hybrid search, knowledge graph, sleep-consolidation lifecycle, expert routing (HMoE), and a graph-Laplacian diffusion subsystem driving decay, consolidation, auto-link, and spectral retrieval. 63 MCP tools. Local, no cloud.
nuget MIT ★ 7 -
Cross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited neuroscience mechanisms, local-first SQLite/PostgreSQL, hybrid retrieval, decay-based consolidation, and reproducible benchmarks. Claude adds optional automatic lifecycle hooks.
pypi MIT ★ 77 -
GSC Wizard plugin for Claude Code, OpenClaw, Codex, Cursor and Gemini CLI: analyze Google Search Console, Bing and GA4 data with SEO audits, content decay, cannibalization, quick wins and weekly reports.
MIT -
Temporal memory system for AI assistants with human-like forgetting curves. All data stored locally in human-readable formats: JSONL for short-term memory, Markdown (Obsidian-compatible) for long-term. Memories naturally decay unless reinforced. Features knowledge graphs, smart prompting, and MCP server integration for Claude.
pypi AGPL-3.0 ★ 39 -
The agent memory that takes it back: correct a fact once and the retired value stops coming back, by key, with no LLM in the loop. Long-term memory for AI agents in a zero-dependency single file + MCP server, with value-ranked recall, per-type decay, consolidation, revert, and tamper-evident erasure.
pypi MIT -
Nornicdb is a distributed low-latency, Graph+Vector, Temporal MVCC with all sub-ms HNSW search, graph traversal, and writes. Using Neo4j Bolt/Cypher and qdrant's gRPC means you can switch with no changes while adding intelligent features like schemas, managed embeddings, reranking+llm, GPU accel, Auto-TLP, Policy-based Memory Decay, and MCP server.
go MIT ★ 931 -
SEO Performanceno update data
Post-publish SEO performance MCP. Unifies **Google Search Console, Matomo, GA4, Microsoft Clarity, and AI-citation signals** per URL and emits a **verdict per post** (refresh / expand / merge / kill / double_down / hold) with deterministic reason codes and a 0-1 confidence score. Reporting only — never mutates posts. Works with any CMS via XML sitemap; optional Ghost Admin API integration for richer metadata. ## Tools - **posts.list** — discover posts via XML sitemap, JSON override, Ghost Admin API, or explicit URL list. - **posts.snapshot** — unified 30/60/90-day signal pull across every configured source for one URL. - **posts.decay_curve** — weekly GSC bucket + decay / plateau / growth classification. - **posts.verdict** — rule-based verdict engine: refresh, expand, merge, kill, double_down, hold. - **posts.refresh_brief** — markdown brief: verdict + reasons + numbers + suggested actions. - **posts.cite_loss** — list of LLMs that previously cited this URL but no longer do. - **cohort.report** — verdict engine across a cohort, ranked by verdict priority + confidence. - **gsc.quick_wins** — pages at positions 5-15 with low CTR, ranked by impressions. ## Prompts - **audit_cohort** — run cohort.report and generate refresh briefs for every actionable URL. - **find_quick_wins** — propose query-verbatim title and H1 rewrites for SERP underperformers. - **citation_loss_sweep** — find URLs that lost LLM citations and recover them. ## How it works Each source is best-effort: if its env vars are missing the field is omitted. Returns whatever is available. Optional DuckDB cache layer for historical comparisons. Platform-agnostic — works with WordPress, Hugo, Astro, Next.js, Webflow, Framer, Wix, Squarespace, Substack, Ghost, and any CMS that exposes a sitemap.
smithery -
Mnemex: Temporal memory management for AI assistants with human-like dynamics
pypi MIT -
cortexgraphgithub.com/prefrontal-systems/cortexgraphupdated this year
CortexGraph: Temporal memory management for AI assistants with human-like dynamics
pypi AGPL-3.0 -
Persistent memory MCP server for AI agents — Rust, 19 tools, knowledge graph, Hebbian learning, episodic memory, contradiction detection, prospective triggers, Bayesian calibration, zero-config Docker setup.
npm Apache-2.0 ★ 30