/ ml free
For chat assistants, coding agents & hobby projects.
- 10,000 ingests + 1,000 retrievals / mo
- Zero feature locks · All capabilities
- Graph & Relational Memory · Included
- Code & symbol recall · Included
- 5 concurrent requests
For zero-trust security, / ml only stores the SHA-256 fingerprint of your key. Copy your key or paste the Agent Setup Prompt directly into your AI agent to set everything up automatically.
sml_live_...
Read https://slashml.ai/llms.txt and set up / ml as our AI memory system using SLASHML_API_KEY="sml_live_...".
You are about to permanently revoke Production Key. Any agents or services using this key will immediately receive HTTP 401 Unauthorized.
The most accurate memory retrieval, instant write, sub-millisecond recall, for all your AIs.
Don’t wire it up by hand. Copy this instruction into Claude Code, Cursor, Windsurf, OpenClaw, or any agent—it will install / ml or migrate your existing Mem0 / Zep / Honcho codebase automatically.
Read https://slashml.ai/llms.txt and set up / ml as our AI memory system using SLASHML_API_KEY="$SLASHML_API_KEY".
curl -X POST https://api.slashml.ai/v1/memories/ \
-H "Authorization: Bearer $SLASHML_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"messages": [{"role": "user", "content": "Production DB migrated to CockroachDB with 6.41ms GDPR unlearning."}],
"user_id": "agent_prod_01"
}'
curl -X POST https://api.slashml.ai/v1/memories/search/ \
-H "Authorization: Bearer $SLASHML_API_KEY" \
-H "Content-Type: application/json" \
-d '{"query": "Where is the production database hosted?", "user_id": "agent_prod_01"}'
from slashml import Memory
m = Memory(api_key="$SLASHML_API_KEY")
# 1. Instant write (0.76 ms, $0 LLM write tax — searchable immediately)
m.add("Auth service uses Ed25519 tokens.", user_id="dev_01")
# 2. Sub-millisecond Graph + Relational recall (0.86 ms p50, 80% lower token cost)
hits = m.search("What signing algorithm does auth use?", user_id="dev_01")
print(hits["results"])
{
"mcpServers": {
"ml-memory": {
"command": "npx",
"args": ["-y", "@slashml/memory", "--workspace", "."],
"env": {
"SLASHML_API_KEY": "$SLASHML_API_KEY"
}
}
}
}
All features. Free. Zero feature locks across all tiers.
The best memory for production agents & startups: 100,000 unified ops/mo for $19/mo with Graph & Relational Memory included and 80% lower LLM prompt token cost.
Keys are cryptographically hashed via SHA-256 and bound to your isolated tenant vault. Revoking a key invalidates it immediately in 0 seconds.
| Key Name | Secret Prefix | SHA-256 Fingerprint | Created | Status | Action |
|---|
Assimilate facts and run live sub-millisecond queries against your isolated tenant state.
Surgical 6.41 ms GDPR unlearning & zero-lock-in JSON export.
For chat assistants, coding agents & hobby projects.
The best memory for production agents & startups.
High-throughput multi-tenant memory infrastructure.
Dedicated appliance inside your own VPC or on-prem.
Set a hard monthly USD ceiling on pay-as-you-go overages. The API gateway automatically returns HTTP 402 if your cap is reached — zero surprise bills.
Bind your corporate domain (e.g. acme.com) to Okta, Microsoft Entra ID, Google Workspace, or WorkOS.
Zero-PII audit trail of inbox verifications, key provisioning, revocations, and tier events.