Now available — 35 MCP tools · Shared Spaces · JWT/DID auth

Zero-LLM graph memory
for every AI agent.
Free to start.

Zero LLM inference at write time — no token surprises, no multi-second extraction penalty. Sub-millisecond in-process engine ops, graph-native from day one — powered by GraphPalace's Rust/LadybugDB engine. 35 MCP tools. Works with anything.

0.035ms
Engine write p95
in-process · no LLM
35
MCP tools
JSON-RPC 2.0
Free
Graph tier
vs $249/mo gate

No credit card required · 3 agents · Graph memory included

am-cli — memory.agentverse.ai⚡ no LLM at write
zero LLM at write timeGraphPalace v0.1

Zero LLM calls · LadybugDB graph engine · Pheromone-weighted retrieval

⚡ Zero LLM at write — no ~2–3s extraction penalty (0.035ms in-process engine)🔷 Zero-LLM graph memory — free at every tier🔌 35 MCP tools · 6 integrations🚫 No token surprises — ever

Graph memory in minutes, not months.

Five lines to connect. One call to write. Zero config to get graph-native entity extraction. No embedding pipelines, no LLM chains, no separate graph database to manage.

  • Install: pip install agentverse-memory
  • Connect any agent framework in < 5 minutes
  • 35 MCP tools — Claude Desktop, Cursor, LangChain, CrewAI, FastAPI, Google ADK
  • Multi-hop graph queries out of the box
quickstart.ts
import { AgentverseMemory } from "@fetchai/agentverse-memory";
const memory = new AgentverseMemory({
apiKey: process.env.AM_API_KEY,
});
// Store — no LLM at write; sub-ms in-process engine op
await memory.store({
content: "Alice prefers dark roast coffee",
type: "semantic",
});
// Query — graph-traversal + pheromone ranking
const result = await memory.query(
"what does Alice prefer?"
);
// → { answer: "dark roast", confidence: 0.97,
// via: "graph trail" }

Built different. Priced differently.

GraphPalace's Rust/LadybugDB architecture changes what's possible at each price point. When writes don't require LLM calls, graph memory can be free.

Zero-LLM Writes

No LLM calls at write time. GraphPalace uses TF-IDF + LadybugDB — the in-process engine write op is sub-millisecond (0.035ms p95 in am-local), so writes carry none of the ~2–3s LLM-extraction penalty that LLM-based systems pay. Predictable cost, no token surprises, 96% entity recall.

🔷

Graph Memory at Every Tier

Knowledge graphs, entity relationships, and multi-hop queries — included on the free tier. Mem0: $249/mo. RetainDB: $20/mo (LLM write). We: $0, zero-LLM.

🔌

Native MCP Integration

35 Model Context Protocol tools over JSON-RPC 2.0. Drop into Claude Desktop, Cursor, LangChain, CrewAI, FastAPI, Google ADK — any MCP-compatible framework. Published as io.github.fetchai/agentverse-memory on the MCP Registry.

🐜

Pheromone-Guided Retrieval

Stigmergic memory trails with 5 decay types. The most relevant memories surface naturally — no manual ranking, no prompt engineering.

🏛️

4 Memory Types

Episodic, semantic, procedural, and working memory — all four types available at every tier. Each backed by the LadybugDB graph engine (active fork of Kùzu).

🔗

Cross-Agent Memory Sharing

5 shared space tools with JWT/DID-authenticated access. Create, join, store, and query across agents — securely, verifiably. Self-host with Docker Compose or use managed Cloud Run.

How we compare

RetainDB narrowed the graph pricing gap to $20/mo — but every competitor still calls an LLM at write time. That's the moat: no ~2–3s LLM-extraction penalty per write (our in-process engine write is sub-ms), zero token costs, free graph tier.

Feature
Agentverse Memory
Free → $99/mo
Mem0
$19 → $249/mo
RetainDB
$0 → $99/mo
Zep
$125/mo+
Knowledge graphAll tiers$249/mo onlyFrom $20/mo$125/mo+
LLM calls at write timeNeverEvery writeEvery writeEvery write
LLM write penaltyNone (0.035ms engine)~2.59s~2–3s est.Not published
MCP tools35 toolsLimitedNot publishedLimited
Pheromone retrieval
Active Inference agentsPro+
Free tier graph memory
Pricing at graph tierFree$249/mo$20/mo$125/mo

Data as of May 2026. Mem0 write latency ~2.59s (LLM extraction, end-to-end). RetainDB write latency ~2–3s est. (LLM extraction, not independently verified). Agentverse Memory in-process engine write p95: 0.035ms (am-local, no LLM step); deployed end-to-end latency varies with payload and namespace size (light requests ~200–260ms; heavy multi-evidence retrieval currently several seconds — being optimized).

Graph at $20/mo sounds good until you see 2–3s write latency.

RetainDB builds its knowledge graph using LLM extraction at write time. Every remember() call invokes an LLM — 2–3 seconds of write latency per operation, plus token costs that scale with every byte you ingest. LLM API outages block memory writes entirely.

Agentverse Memory uses TF-IDF + LadybugDB. No LLM at write time. 0.035ms p95 in-process engine write — no extraction penalty. Graph is free here — and writes never wait on an LLM.

Why GraphPalace is different

Most memory systems call an LLM to extract entities at write time. GraphPalace uses TF-IDF + LadybugDB — classical information retrieval in a Rust binary. No API call, no token cost, no latency.

Mem0 / Zep / RetainDB approach
1memory.add("Alice approved Q3 budget")0ms
2Call embedding API+50ms
3Call LLM: extract entities & relations+2,500ms
4Parse LLM response+10ms
5Write to graph DB+30ms
Total: ~2,590ms · LLM bill: unpredictable
GraphPalace approach
1memory.add("Alice approved Q3 budget")0ms
2TF-IDF entity extraction (Rust)+1ms
3Write to LadybugDB (in-process)0.035ms p95
4Update pheromone trails<1ms
Done<5ms
In-process write path: <5ms · Engine write p95: 0.035ms · LLM: $0

Simple pricing. Graph included.

No credit math. No graph gates. No token surprises.

Explorer
Free
3 agents
50K ops/mo
✓ Graph memory
Graph included
Start Free
Builder
$19/mo
25 agents
500K ops/mo
✓ Graph memory
+ A* pathfinding
Start Builder
Most Popular
Pro
$99/mo
Unlimited agents
5M ops/mo
✓ Graph memory
+ Active Inference
Start Pro
Enterprise
Custom
Unlimited agents
Custom ops
✓ Graph memory
SOC 2 · BYOC
Talk to Sales

Zero-LLM writes. Graph at every tier.

Start building memory-enabled agents today. Three agents, full graph support, pheromone retrieval — free, no credit card. No LLM at write time, zero token surprises.