io.github.jyswee/agenticmemory
agenticmemory
io.github.jyswee/agenticmemory costs 4 755 tokens of context per session. It has 46 tool definitions. That is 2.4 % of a 200k window. Measured 2026-10-03.
Persistent memory for AI agents — history, context, semantic search, queues. 46 tools, stdio/SSE.
alive probed 2026-10-03 · HTTP 200
46tools
4.8ktokens for the tool definitions
2.4 %of a 200k context window
4.4 sto initialize
294 msto list tools
- Endpoint
- https://mcp.agenticmemory.ai/sse (sse)
- Host
- mcp.agenticmemory.ai
- Reports itself as
- agenticmemory 1.3.0
- Capabilities
- tools
- Instructions
- none
- Repository
- https://github.com/jyswee/agenticmemory
- Website
- https://agenticmemory.ai
- Registry
- active, updated 2026-09-23 · registry entry
- Reachable
- 1 of the last 2 probes
Most expensive tools
| Tool | Tokens | Share of this server |
|---|---|---|
| stream_group | 281 | 6 % |
| entry | 231 | 5 % |
| kv_hash | 224 | 5 % |
| knowledge | 195 | 4 % |
| entity | 168 | 4 % |
History
We add a row when the result changes. A server with no change keeps its last row.
| Probed | Result | Init | Tools | Tokens |
|---|---|---|---|---|
| 2026-10-03 20:38 | alive | 4.4 s | 46 | 4.8k |
| 2026-10-03 17:54 | not MCP |
Badge
[](https://mcp-pulse.ulehla.dev/s/io.github.jyswee/agenticmemory)