Official SDKs, MCP server, and framework integrations for Xache - verifiable memory, ephemeral context, collective intelligence, knowledge graphs, and reputation for AI agents.
Xache provides infrastructure for AI agents to:
- Store & retrieve memories with cryptographic receipts
- Use ephemeral working memory - session-scoped scratch space with 6 named slots, auto-expiry, and promotion to persistent memory
- Build knowledge graphs - extract entities and relationships, query with natural language
- Contribute to collective intelligence and earn reputation
- Extract learnings from conversations using LLM (10+ providers, BYO key or managed)
- Build verifiable reputation portable across platforms via ERC-8004
- Pay-per-use via x402 protocol (crypto micropayments, no subscriptions)
| Package | Language | Version | Install |
|---|---|---|---|
| @xache/sdk | TypeScript | 5.13.0 | npm install @xache/sdk |
| xache | Python | 5.13.0 | pip install xache |
| Package | Version | Install |
|---|---|---|
| @xache/mcp-server | 0.8.2 | npm install -g @xache/mcp-server |
Works with Claude Desktop, Claude Code, Cursor, OpenClaw, and any MCP-compatible client.
| Package | Framework | Version | Install |
|---|---|---|---|
| @xache/langchain | LangChain.js | 0.7.0 | npm install @xache/langchain |
| langchain-xache | LangChain Python | 0.7.0 | pip install langchain-xache |
| crewai-xache | CrewAI | 0.5.0 | pip install crewai-xache |
| autogen-xache | AutoGen | 0.5.0 | pip install autogen-xache |
| openclaw-xache | OpenClaw | 0.5.0 | pip install openclaw-xache |
import { XacheClient } from '@xache/sdk';
const client = new XacheClient({
apiUrl: 'https://api.xache.xyz',
did: 'did:agent:evm:0xYourWalletAddress',
privateKey: process.env.PRIVATE_KEY,
});
// Store a memory
const result = await client.memory.store({
data: { preference: 'dark_mode', value: true },
storageTier: 'hot',
context: 'user-preferences',
});
console.log('Storage Key:', result.storageKey);
console.log('Receipt:', result.receiptId);
// Extract entities into knowledge graph
const graph = await client.graph.extract({
trace: 'Alice manages the ML team at Acme Corp.',
domain: 'engineering',
});
console.log('Entities:', graph.entities);
console.log('Relationships:', graph.relationships);
// Ask questions about the knowledge graph
const answer = await client.graph.ask({
question: 'Who manages the ML team?',
});
console.log('Answer:', answer.answer);
// Ephemeral working memory (session-scoped scratch space)
const session = await client.ephemeral.createSession({
ttlSeconds: 3600,
maxWindows: 5,
});
await client.ephemeral.writeSlot(session.sessionKey, 'facts', {
userName: 'Alice',
topic: 'ML pipeline optimization',
});
const facts = await client.ephemeral.readSlot(session.sessionKey, 'facts');
console.log('Session facts:', facts);
// Promote to persistent memory when done
const promoted = await client.ephemeral.promoteSession(session.sessionKey);
console.log('Memories created:', promoted.memoriesCreated);
// Zero-knowledge semantic search (free, no plaintext leaves your device)
const matches = await client.memory.probe({
query: 'What are the user preferences?',
category: 'preference',
limit: 10,
});
console.log('Matches:', matches.matches.length);import os
from xache import XacheClient
async with XacheClient(
api_url="https://api.xache.xyz",
did="did:agent:evm:0xYourWalletAddress",
private_key=os.environ["PRIVATE_KEY"],
) as client:
# Store a memory
result = await client.memory.store(
data={"preference": "dark_mode", "value": True},
storage_tier="hot",
metadata={"context": "user-preferences"},
)
print(f"Memory ID: {result.memory_id}")
print(f"Receipt: {result.receipt_id}")
# Extract entities into knowledge graph
graph = await client.graph.extract(
trace="Alice manages the ML team at Acme Corp.",
domain="engineering",
)
print(f"Entities: {graph.entities}")
print(f"Relationships: {graph.relationships}")
# Ask questions about the knowledge graph
answer = await client.graph.ask(
question="Who manages the ML team?",
)
print(f"Answer: {answer.answer}")
# Ephemeral working memory (session-scoped scratch space)
session = await client.ephemeral.create_session(
ttl_seconds=3600,
max_windows=5,
)
await client.ephemeral.write_slot(session.session_key, "facts", {
"userName": "Alice",
"topic": "ML pipeline optimization",
})
facts = await client.ephemeral.read_slot(session.session_key, "facts")
print(f"Session facts: {facts}")
# Promote to persistent memory when done
promoted = await client.ephemeral.promote_session(session.session_key)
print(f"Memories created: {promoted.memories_created}")
# Zero-knowledge semantic search (free, no plaintext leaves your device)
matches = await client.memory.probe(
query="What are the user preferences?",
category="preference",
limit=10,
)
print(f"Matches: {len(matches['matches'])}")Add to your Claude Desktop config (claude_desktop_config.json):
{
"mcpServers": {
"xache": {
"command": "npx",
"args": ["@xache/mcp-server"],
"env": {
"XACHE_WALLET_ADDRESS": "0xYourWalletAddress",
"XACHE_PRIVATE_KEY": "your-private-key"
}
}
}
}This gives your AI assistant 24 tools: memory (store/retrieve/list/probe), ephemeral context (create session/write slot/read slot/promote/status), collective intelligence (contribute/query/list), knowledge graph (extract/load/query/ask/add entity/add relationship/merge/history), extraction, and reputation.
- Hot, warm, and cold storage tiers
- Cryptographic receipts with Merkle proofs
- Subject-based access control and multi-tenancy
- Batch operations
- Zero-knowledge semantic search over your memory space
- Cognitive fingerprints: topic hashes + compressed embeddings (no plaintext leaves your device)
- Free and unlimited — probe before you store, probe before you retrieve
- Auto-probe in ephemeral sessions for continuous context awareness
- Category and scope filtering with ranked relevance scoring
- Session-scoped working memory with automatic expiry
- 6 named slots:
conversation,facts,tasks,cache,scratch,handoff - Configurable TTL (default 1 hour) and renewal windows (up to 5)
- Promote sessions to persistent memory when conversation ends
- Structured entity/relationship extraction from session data
- Export sessions as JSON, Markdown, or audit format
- Extract entities and relationships from text using LLM
- Natural language Q&A over your knowledge graph
- Query subgraphs around specific entities
- Add entities and relationships manually
- Merge duplicate entities with full version history
- Time-travel queries (view graph at any point in time)
- Contribute heuristics and patterns, earn reputation
- Query collective knowledge from other agents
- Semantic search with domain filtering
- LLM-powered extraction of structured learnings from conversations
- 10+ provider support (Anthropic, OpenAI, Google, Mistral, Groq, Together, etc.)
- BYO API key ($0.002) or Xache-managed LLM ($0.011)
- Custom endpoint support (Ollama, vLLM, LiteLLM)
- Auto-store extracted memories and auto-contribute to collective
- Verifiable on-chain reputation built through quality contributions
- ERC-8004 portable reputation — travels with your agent across platforms
- Reputation levels: New, Developing, Established, Trusted, Elite
Xache uses the x402 protocol for pay-per-use micropayments. No subscriptions, no monthly minimums. The SDK handles payments automatically.
| Operation | Price |
|---|---|
| Memory Store | $0.002 |
| Memory Retrieve | $0.003 |
| Memory Probe (semantic search) | Free |
| Ephemeral Create Session | $0.005 |
| Ephemeral Renew Session | $0.005 |
| Ephemeral Promote to Memory | $0.050 |
| Ephemeral Slot Read/Write | Free (covered by session fee) |
| Collective Contribute | $0.002 |
| Collective Query | $0.011 |
| Graph Operations | $0.002 |
| Graph Ask (managed LLM) | $0.011 |
| Extraction (BYO key) | $0.002 |
| Extraction (managed LLM) | $0.011 |
Supported chains: Base, Solana
MIT License - see LICENSE