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.
-
Open-source causal graph memory for AI agents. 85.55 on LoCoMo under a frozen, reproducible protocol. MCP server with ACT-R scoring, spreading activation, and active forgetting.
AGPL-3.0 ★ 31 -
OS-style paging for an agent's context window: FIFO, LRU, ARC and recency-importance eviction, SQLite recall and archival storage, an MCP server, and a LoCoMo replay benchmark of evidence kept in context at 1K/2K/4K-token budgets.
MIT -
Auditable memory layer for AI agents: zero-LLM-call local ingest (~10ms/msg, air-gapped), matches Mem0 on accuracy at ~1000x lower ingest cost, bi-temporal belief-state, MCP server. Honest LoCoMo/LongMemEval benchmarks. Open source (Apache-2.0).
npm Apache-2.0 ★ 12 -
Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.
pypi NOASSERTION ★ 274 -
memforgegithub.com/MemForgeAI/memforgeupdated this year
The open-source memory layer for AI agents. MCP-native, single Postgres, #1 on LOCOMO benchmark.
npm NOASSERTION ★ 2 -
0gmemgithub.com/loganionian/0gmemupdated this year
Long-term conversational memory system for AI agents — cell-based architecture with hybrid BM25 + semantic retrieval. 96% accuracy on LoCoMo benchmark.
MIT ★ 11 -
Self-hosted MCP server for AI agent memory — 14 core tools, profile-based tiering (86+ available). 88.2% LoCoMo. Works with Claude, Cursor, Windsurf.
npm MIT ★ 9 -
Long-term memory for AI coding agents — remembers project rules across sessions at $0 AI cost (MCP server, SQLite/PostgreSQL). 90.26% on Snap LoCoMo.
MIT ★ 83 -
Ebbtide MCP: local long-term memory for AI agents. Hybrid keyword + embedding recall, fact updates, and a forgetting curve for bounded stores; benchmarked on LongMemEval and LoCoMo.
MIT -
Long-term memory for LLM assistants: LLM extraction with JSON-schema validation, hybrid recall of memories (dense + BM25, RRF) plus raw turns, served over HTTP and MCP, and a LoRA-distilled Qwen3.5-0.8B extractor that runs locally via Ollama. Benchmarked on LoCoMo. Rebuilt from a 26th-place Neurohack (IIT Guwahati) entry.
★ 1 -
Persistent local memory for AI coding agents — Claude Code, Codex CLI, Cursor, any MCP client. Temporal knowledge graph, procedural memory, AST codebase ingest, cross-project analogy. LongMemEval R@5 95.1%, LoCoMo 0.607, BEAM 1M 0.448. 74 MCP tools, 9 IDEs, 100% local.
pypi MIT ★ 77