AxonPG
Provides full auto-setup for Hermes Agent, merging the AxonPG MCP server into Hermes configuration and installing an axonpg-memory skill for durable agent memory workflows.
Supports NVIDIA NIM APIs for embeddings and LLM-assisted memory consolidation.
Supports local Ollama for multilingual embeddings and LLM-assisted memory consolidation.
Supports OpenAI embeddings and chat completions for memory consolidation, plus custom OpenAI-compatible endpoints.
Uses PostgreSQL with pgvector, pg_trgm, and unaccent as the primary memory backend, enabling hybrid recall across knowledge graph, episodic, semantic, and prospective memory layers.
Provides a zero-Docker SQLite + FTS5 --lite backend for the same cognitive memory layers, suitable for laptops and CI environments.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
AxonPG
Multilingual PostgreSQL-Native Cognitive Memory Engine for AI Agents
English • Español • Português • Français
AxonPG gives AI agents (such as Hermes Agent, OpenClaw, Claude Desktop/Code, Cursor, and Antigravity) durable, structured, all-language memory backed by a single PostgreSQL + pgvector + pg_trgm + unaccent instance — or an instant Zero-Docker SQLite + FTS5 (--lite) fallback for laptops and CI.
Instead of drowning LLM context windows with raw transcripts, AxonPG maintains 4 cognitive layers while keeping exact facts (IDs, numbers, dates, currencies, error codes) lossless inside structured JSON (hard_facts):
flowchart LR
Agent["AI Agent (Hermes / OpenClaw / MCP)"] -->|"MCP tools"| Server["AxonPG MCPServer"]
Server --> Recall["Hybrid RRF Recall\n(FTS + Trigram/CJK + Vector)"]
Server --> Consolidate["Sleep Consolidator\n(Optional LLM or Deterministic)"]
Recall --> L1["1. Knowledge Graph\n(Entities + Aliases + Relations)"]
Recall --> L2["2. Episodic MemCells\n(Outcomes + hard_facts)"]
Recall --> L3["3. Semantic Memories\n(fact_key contradiction supersession)"]
Recall --> L4["4. Prospective Foresights\n(Auto-expiring reminders)"]
L1 & L2 & L3 & L4 --> DB[("PostgreSQL pgvector\nOR SQLite --lite")]Why AxonPG?
True Multilingual Support (All Scripts): Uses Unicode NFC normalization, non-destructive accent folding (
camión↔camion), PostgreSQL'simple'dictionary +axon_unaccent, SQLite FTS5unicode61, substring matching for CJK (日本語,中文,한국어), Cyrillic, and Arabic, plus multilingual embeddings by default (paraphrase-multilingual-MiniLM-L12-v2).One Database, Zero Stack Bloat: Runs on a single PostgreSQL container (
pgvector/pgvector:pg16) or zero-dependency--liteSQLite WAL database. No Neo4j, Qdrant, or Redis required.Lossless
hard_facts+ Fact Supersession: Updating afact_keyautomatically marks older contradicting facts assuperseded_by, while exact parameters insidehard_factsare never rounded or paraphrased.Plug & Play Agent Setup (
axonpg init): Interactive multilingual setup (en,es,pt,fr) with safe non-destructive MCP configuration for Hermes Agent, OpenClaw, and Generic MCP clients.Multi-Provider Freedom: Works offline on CPU (
fastembedONNX), locally (ollama), or via cloud APIs (nvidiaNIM,openrouter,gemini,openai,customOpenAI-compatible).
Related MCP server: Recall
Supported Agent Comparison (axonpg init)
Agent | Integration Mode | What | Best For |
Hermes Agent (default) | Full auto-setup | Merges | Python-native workflows, skill evolution, token efficiency |
OpenClaw | Schema-safe MCP bundle | Writes standalone | Node.js/TS multi-channel gateways & Control UI |
Generic MCP | Standard | Generates | IDE coding assistants & desktop clients |
Quickstart
Option A: 1-Line Installer
Linux / macOS:
curl -fsSL https://raw.githubusercontent.com/ricardo2591/axonpg/main/installers/install.sh | bashWindows (PowerShell):
irm https://raw.githubusercontent.com/ricardo2591/axonpg/main/installers/install.ps1 | iexOption B: Manual Local Setup
git clone https://github.com/ricardo2591/axonpg.git
cd axonpg
python -m venv .venv
source .venv/bin/activate # Windows PowerShell: .venv\Scripts\Activate.ps1
pip install -e ".[local]"Start PostgreSQL (pgvector):
docker compose up -d
axonpg init --mode docker --agent hermes --lang en
axonpg doctorOr start in Zero-Docker --lite mode (instant laptop/CI mode):
axonpg init --mode lite --agent hermes --embed-provider fastembed
axonpg doctorMCP Tools Exposed
When running axonpg serve over stdio or streamable-http, agents get 9 structured tools:
memory_recall— Token-budgeted hybrid recall across Knowledge Graph, Semantic Memories, Episodic Lessons, and Active Foresights.memory_upsert_entity— Add or update entities with multilingual aliases and JSON properties.memory_add_relation— Connect entities with weighted, temporally-bounded edges.memory_record_episode— Log task execution outcomes (success/failure/partial) with exacthard_facts.memory_upsert_fact— Store current truth; auto-supersedes outdated active facts sharing the samefact_key.memory_add_foresight— Register deadlines/follow-ups with automaticexpires_atarchival.memory_complete_foresight— Mark an active foresight as completed.memory_consolidate— Run sleep-time synthesis of unconsolidated episodes (deterministic or LLM-assisted).memory_stats— Inspect active counts per memory layer.
Embedding & LLM Consolidation Providers
Configure in .env (never committed) or during axonpg init:
Provider | Embeddings ( | Consolidation LLM ( |
|
| — |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| Any OpenAI | Any OpenAI |
| Keyword/FTS/trigram fallback only | Deterministic offline consolidation (default) |
Security Note: Generated agent configs (
hermes,openclaw,axonpg.mcp.json) store zero secrets. They passAXONPG_ENV_FILEpointing to your local.envfile (chmod 600on POSIX).
License
Apache License 2.0 — see LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Persistent memory, knowledge graph, task management and more for AI agents via MCP.
Persistent, inspectable memory for AI agents with lineage, correction, and a hosted MCP endpoint.
Persistent memory and knowledge management for AI agents with semantic search and 50+ tools.
Persistent memory for AI agents across Claude, ChatGPT and any MCP client.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenancePersistent, semantically-searchable memory for AI agents using local PostgreSQL, pgvector, and Ollama embeddings, exposed via MCP with hybrid retrieval, knowledge graph, and auto-recall hook.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to store and semantically retrieve durable memories across sessions via MCP or REST, with tools for remembering, recalling, asking, updating, and forgetting memories.17 npmMIT
- FlicenseNot gradedqualityBmaintenanceEnables agents to store conversational turns in a single SQLite store and recall relevant context through lexical, entity, dense, and recent views without an LLM in the recall loop. It exposes MCP tools for remembering, bulk ingest, recall, stats, and session deletion, with persistent indexes and zero-token maintenance.-
- FlicenseAqualityCmaintenanceEnables AI agents to persist, search, and query shared memories in PostgreSQL through hybrid retrieval, preset answers, and AI-to-AI consultation via MCP.9-