vbcherepanov/total-agent-memory
by Various
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 analo
MCP
vbcherepanov/total-agent-memory
Added 8 Sept 2026
Overview
Persistent local memory system for AI coding agents, providing a temporal knowledge graph, procedural memory, AST-based codebase ingestion, and cross-project analogy. It integrates with multiple AI coding tools via 74 MCP tools and supports 9 IDEs, with all data stored locally.
Best for
Best for
Developers and teams using AI coding agents who need persistent, private, cross-project memory
Use cases
- Give AI agents long-term memory across coding sessions and projects
- Enable cross-project code reuse and pattern recognition via analogy
- Index codebases using AST for structured, queryable project knowledge
How to use
Install
pip install "total-agent-memory[rerank]" # pip / uvx / pipx Tools exposed
single-hopmulti-hopopen-domaincontradiction_resolutiontemporal_reasoningknowledge_updatemulti_session_reasoninginformation_extractionpreference_followingevent_orderinginstruction_followingknowledge-updatemulti-sessionsingle-session-usersingle-session-assistanttemporal-reasoningsingle-session-preferenceMCP-native
Tested with
Claude Code, Cursor, Windsurf, Cline, Continue, VS Code, ChatGPT
Notes
Persistent local memory system for AI coding agents, providing a temporal knowledge graph, procedural memory, AST-based codebase ingestion, and cross-project analogy. It integrates with multiple AI coding tools via 74 MCP tools and supports 9 IDEs, with all data stored locally.
67 stars on GitHub. Last updated 2026-09-07. Licensed MIT.
Use cases
- Give AI agents long-term memory across coding sessions and projects
- Enable cross-project code reuse and pattern recognition via analogy
- Index codebases using AST for structured, queryable project knowledge
Pros
- 100% local storage keeps code and metadata private
- Broad IDE and agent compatibility through MCP and 9 IDE integrations
- Benchmarked on LongMemEval, LoCoMo, and BEAM with strong retrieval scores
Cons
- Requires setup and maintenance of a local memory service
- Performance depends on the quality and frequency of AST ingestion
- May add overhead for very large or rapidly changing codebases
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- 100% local storage keeps code and metadata private
- Broad IDE and agent compatibility through MCP and 9 IDE integrations
- Benchmarked on LongMemEval, LoCoMo, and BEAM with strong retrieval scores
Cons
- Requires setup and maintenance of a local memory service
- Performance depends on the quality and frequency of AST ingestion
- May add overhead for very large or rapidly changing codebases
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.
