Back to MCP servers

total-agent-memory

MCP serverGitHubActivePython

Persistent local memory for AI coding agents — Claude Code, Codex CLI, Cursor, any MCP client. Temporal knowledge graph, procedural memory, AST codebase ingest, cross-project analogy. LongMemEval R@5 95.1%, LoCoMo 0.607, BEAM 1M 0.448. 74 MCP tools, 9 IDEs, 100% local.

Description provenance: Original source

Open canonical source

Measured: Oct 20, 2026 · 69 observations

Domains & Uses

Domains
Agents, skills and MCP
Uses
Agent skills, Retrieval-augmented generation (RAG), Code assistants

Check at the source

Compatibility and prerequisites must be checked in the official documentation.

https://github.com/vbcherepanov/total-agent-memory

Classifications

Nature
Tool

Measurement history

Comparable readings are grouped by signal and unit.

Stars

73stars · Oct 20, 2026

+5 (+7.4 %)since Sep 22, 2026

Sep 22, 2026 : 68 starsSep 23, 2026 : 69 starsSep 24, 2026 : 69 starsSep 25, 2026 : 70 starsSep 26, 2026 : 72 starsSep 27, 2026 : 72 starsSep 28, 2026 : 72 starsSep 29, 2026 : 72 starsSep 30, 2026 : 71 starsOct 1, 2026 : 71 starsOct 2, 2026 : 71 starsOct 3, 2026 : 71 starsOct 4, 2026 : 71 starsOct 5, 2026 : 71 starsOct 6, 2026 : 71 starsOct 7, 2026 : 71 starsOct 8, 2026 : 71 starsOct 9, 2026 : 72 starsOct 10, 2026 : 73 starsOct 11, 2026 : 73 starsOct 12, 2026 : 73 starsOct 13, 2026 : 73 starsOct 14, 2026 : 73 starsOct 15, 2026 : 73 starsOct 16, 2026 : 73 starsOct 17, 2026 : 73 starsOct 18, 2026 : 73 starsOct 19, 2026 : 73 starsOct 20, 2026 : 73 stars
Exact values · 29 readings
MeasuredstarsChange
730
730
730
730
730
730
730
730
730
730
73+1
72+1
710
710
710
710
710
710
710
710
71-1
720
720
720
72+2
70+1
690
69+1
68·