TOMC

SetupView on GitHub

TOMC is an MCP server by ZipengWu365. TOMC Memory: CPU context compression and task memory for Codex, Claude Code, Cursor, TRAE, WorkBuddy and other MCP clients. It has 264 GitHub stars and ranks #217 of 1,679 in Memory & Knowledge by stars.

Category
Memory & Knowledge
MCP evidence
Listed in the official MCP Registry
Author
ZipengWu365
GitHub stars
264
This week
+0 stars this week (+0%) · +0 forks since 10 Nov 2026
Language
Python
License
MIT (open source)
Last update
2026-11-16
Forks
26
Created
2026-10-06
MCP Registry
io.github.ZipengWu365/tomc-memory
Links
Source

How to install TOMC

MCP Harbor has no install command on record for TOMC, so follow the README in the TOMC repository. Most MCP servers start with a single command (npx -y <package>, uvx <package> or a Docker image) that you add to your client's config. The install guide shows where that goes in Claude Code, Claude Desktop, Cursor and VS Code.

More MCP servers for Python projects

TOMC ranks #251 by GitHub stars among the 1,578 listings in MCP servers for Python projects. That page compares the top entries by stars, license and last update.

Report a problem with this listing · Advertise on MCP Harbor

Frequently asked questions

What is TOMC?

TOMC is an MCP server by ZipengWu365 in the Memory & Knowledge category. TOMC Memory: CPU context compression and task memory for Codex, Claude Code, Cursor, TRAE, WorkBuddy and other MCP clients. It has 264 GitHub stars and ranks #217 of 1,679 in Memory & Knowledge by stars.

Is TOMC free and open source?

The code in the TOMC repository is published under the MIT license, an open-source license that lets you read, modify and reuse the code. The license covers the code only. An app, account or API that TOMC connects to can have its own price and terms, so check those before you rely on it in a commercial product.

What are the alternatives to TOMC?

Other Memory & Knowledge projects on MCP Harbor include open-webui, graphify, claude-mem. Each alternative links to its own page with stars, license and recent activity. The Memory & Knowledge category ranks all 1,679 by stars, and you can re-sort it by growth this week.

Alternatives to TOMC

open-webui · Svelte+629 stars this week (+0.4%)
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
graphifyTrending★ 149,347
Graphify-Labs · Python+4,046 stars this week (+2.8%)
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
thedotmack · TypeScript · MCP evidence: npm package+2,264 stars this week (+2%)
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
ragflow★ 94,304
infiniflow · Go+358 stars this week (+0.4%)
RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.
ruflo★ 81,925
ruvnet · TypeScript · MCP evidence: MCP Registry+528 stars this week (+0.6%)
🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
headroom★ 79,878
headroomlabs-ai · Python+595 stars this week (+0.8%)
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

All 1,679 Memory & Knowledge MCP servers →

Data last updated . Stars and downloads are refreshed every day from GitHub and npm.

Contact MCP Harbor

We reply by email. You can also write to hello@mcpharbor.app.

Report a problem with this listing

TOMCZipengWu365 · /tools/zipengwu365-tomc/

We reply by email.