SlashML (/ml) Persistent Agent Memory & Code Localization
Persistent conversational memory, behavioral code search, and bug localization for AI agents.
Open the source (opens github.com) https://github.com/slashml-ai/ml-memory
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
- Needs credentials: SLASHML_API_KEY. Use a key with the least access you can.
What it is
MCP servers from io.github.slashml-ai.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
npm package (stdio)
@slashml/mcp@1.0.14
From the server's entry in the official MCP Registry
pypi package (stdio)
slashml-memory@1.0.12
From the server's entry in the official MCP Registry
Settings it asks for
SLASHML_API_KEYsecret required · Your SlashML API key (sml_live_...) from https://app.slashml.aiSLASHML_USER_ID· Optional default user or workspace namespaceSLASHML_AGENT_ID· Optional caller agent ID for per-agent read/write access and redaction policiesSLASHML_REDACT_POLICY· Optional default redaction preset or comma-separated sensitive bucketsSLASHML_REDACT_SCOPE· Optional redaction scope: memorize_and_recall or recall_onlySLASHML_API_KEYsecret required · Your SlashML API key (sml_live_...) from https://app.slashml.ai
Related
-
Persistent memory, inline redaction, per-agent access, and code localization for AI agents.
-
Persistent 6-DoF SE(3) spatial world state, object trajectories, and affordances for robotics.
slashml-robotics@1.0.1 -
Sub-millisecond 7-DoF trajectory episode memory and kinematic safety gates for robotics.
-
Language ml
MCP serversISO 639 language tag ml.
-
standard-ml-mcp
MCP serversStandard ML MCP: 20 real tools to read, check, lint, scaffold, build and run Standard ML code.
@mrfentmen/standard-ml-mcp@1.0.0 -
ISO country ML
MCP serversPublic ISO 3166-1 record for ML.