Explore
MCP servers and skills: search, filter by where they run, and compare.
zaxysyndicalt
Local
MCP servers and skills: search, filter by where they run, and compare.
Zaxy turns agent work into durable, auditable memory: a hash-chained Eventloom log as the source of truth, an embedded temporal knowledge graph for reasoning (local-first, no sidecar; Neo4j/Postgres o
PythonMIT★ 17No key
Typed long-term memory for AI agents. One core, an MCP server, and a Hermes plugin.
PythonMIT★ 28No key
Deterministic code-graph context engine for AI coding agents - PostgreSQL + Apache AGE + pgvector, MCP & REST, no LLM in the loop.
PythonMIT★ 75No key
CVE ingestion + enrichment pipeline with an MCP server for AI agents.
PythonMIT★ 38No key
Shared local memory for Claude Code, Cursor, and Codex that stays true to your code.
PythonMIT★ 2Few starsNo key
Persistent semantic memory for SQL databases (Postgres, MySQL, MSSQL, SQLite) — the MCP server with the most ironic name. One-line install for Claude Code, Cursor, and any MCP-compatible client.
PythonMIT★ 4Few starsNo key
MCP server for Beget hosting — 73 tools covering 100% of Beget REST API (sites, domains, DNS, MySQL, FTP, cron, backups, mail)
PythonMIT★ 3Few starsNeeds a key
Local-first, reviewable memory layer for Codex with MCP, lifecycle hooks, and memory governance.
PythonMIT★ 1Few starsNo key
Parse, edit, validate, diff, and encode/decode DBC (CAN database) files in Python
SkillMITFew starsNo key
The Universal Cross-Model Episodic Memory Standard. Local-first, project-scoped SQLite engine for Google Antigravity, Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, and OpenCode. Zero cloud lock-
PythonMIT★ 299No key
MyKG Knowledge Graph Engine: Turn raw files into knowledge graphs with induced ontology
PythonMIT★ 76No key
Evidence-driven skill evolution for Hermes Agent — reports, dry-run proposals, candidate search, and guarded apply
SkillMIT★ 48No key
LLM Reasoning Framework for Scientific Research
PythonMIT★ 32No key
Persistent memory MCP for AI agents — SQLite, knowledge graph, 13-tool Python MCP + 17-tool BrainBar surface with ToolAnnotations
PythonApache-2.0★ 9No key
A task board Claude fills in for itself: a Claude Code plugin that mirrors Claude's task list onto a per-project board, with MCP tools and a local web panel.
PythonMIT★ 13No key
Local-first memory engine for AI-agent teams — private/team/project ACL, associative recall, federated sync, and a built-in MCP server. One SQLite file, no LLM required. Apache-2.0.
PythonApache-2.0★ 7No key
An MCP server allowing AI assistants to use a Neo4j knowledge graph as their primary, dynamic instruction manual and long term project memory with adaptive templating and autonomous tool development t
PythonMIT★ 20No key
Git-versioned, provenance-grounded knowledge layer extracted from a codebase, served to humans and AI agents via MCP
PythonAGPL-3.0★ 9No key
Lightweight persistent memory for AI agents. One SQLite file. Hybrid search. Zero to 12MB.
PythonMIT★ 6No key
A label property graph in a single SQLite file — event-sourced, gated, and MCP-ready. Agent memory you can audit, replay, and undo.
PythonMIT★ 1Few starsNo key
Cross-machine memory for Claude Code: local-first, file-based agent memory that syncs across your own machines.
PythonApache-2.0Few starsNo key
Who stands behind it
