agentmemory-rest-api
This skill provides the HTTP REST API surface for agentmemory, serving as the primary protocol for interacting with the memory server. It enables AI agents to store and retrieve memories via standard HTTP, ensuring efficient knowledge base management and access in various scenarios, such as when a specific protocol is unavailable or when integrating with incompatible hosts. This significantly enhances the agent's adaptability and data interaction capabilities.
npx skills add https://github.com/rohitg00/agentmemory --skill agentmemory-rest-apiBefore / After Comparison
1 组Without a standardized HTTP API, users or developers had to spend significant time manually developing or adapting specific communication protocols for AI agents to interact with memory servers, making the integration process complex and time-consuming.
This skill provides an out-of-the-box HTTP REST API, allowing AI agents to quickly and conveniently store and retrieve memories via a standard protocol. This drastically reduces integration effort and time, improving development efficiency and system compatibility.
REST is agentmemory's primary surface. MCP is a bridge on top of it. Every memory operation has an HTTP endpoint under http://localhost:3111/agentmemory/*.
Quick start
# liveness
curl -fsS http://localhost:3111/agentmemory/livez
# save
curl -X POST http://localhost:3111/agentmemory/remember \
-H "Content-Type: application/json" \
-d '{"content":"chose JWT refresh rotation","concepts":["jwt-refresh-rotation"]}'
# recall
curl -X POST http://localhost:3111/agentmemory/smart-search \
-H "Content-Type: application/json" \
-d '{"query":"auth token strategy","limit":5}'
Auth
By default localhost is open and no auth is needed. When AGENTMEMORY_SECRET is set, every request needs Authorization: Bearer $AGENTMEMORY_SECRET. See agentmemory-config.
Conventions
- Save returns
201, reads return200, validation errors return400. - Handlers whitelist body fields and drop unknown ones, so passing extra keys is safe but ignored.
- The port is configurable with
--portor--instance; streams, viewer, and engine derive from it.
See also
- agentmemory-mcp-tools for the MCP equivalents.
- agentmemory-config for the port quartet and the secret.
Reference
The full endpoint list with methods lives in REFERENCE.md, generated from src/triggers/api.ts.
User Reviews (0)
Write a Review
No reviews yet
Statistics
User Rating
Rate this Skill