mksglu/context-mode

Analysis updated 2026-06-24 · repo last pushed 2026-05-21

★ 14,627TypeScriptAudience · developerComplexity · 4/5MaintainedLicenseSetup · moderate

Mindmap

mindmap
  root((context-mode))
    Inputs
      Agent tool calls
      Raw command output
      Session events
    Outputs
      Compact summaries
      BM25 search results
      Session continuity
    Use Cases
      Save context window space
      Recover after compaction
      Index large data sets
    Tech Stack
      TypeScript
      MCP
      SQLite
      BM25

mindmap root((context-mode)) Inputs Agent tool calls Raw command output Session events Outputs Compact summaries BM25 search results Session continuity Use Cases Save context window space Recover after compaction Index large data sets Tech Stack TypeScript MCP SQLite BM25

Click or tap to explore — scroll the page freely

What do people build with it?

USE CASE 1

Cut context usage on Claude Code or Cursor by sandboxing large tool outputs into small summaries

USE CASE 2

Restore an agent's working memory after a context compaction using BM25 search over a SQLite event log

USE CASE 3

Run Playwright snapshots, log greps, and GitHub issue dumps without flooding the model context

USE CASE 4

Add a Think in Code pattern so the agent writes a script that returns only the answer

What is it built with?

TypeScriptMCPSQLiteBM25

How does it compare?

	mksglu/context-mode	sairyss/domain-driven-hexagon	tonejs/tone.js
Stars	14,627	14,636	14,609
Language	TypeScript	TypeScript	TypeScript
Last pushed	2026-05-21	2024-06-11	2026-05-20
Maintenance	Maintained	Dormant	Maintained
Setup difficulty	moderate	moderate	easy
Complexity	4/5	4/5	3/5
Audience	developer	developer	developer

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · moderate Time to first run · 30min

Automatic routing enforcement only works on platforms with hook support, others need a routing file copied into the project by hand.

Elastic License v2 lets you use and modify the code for free, but you cannot offer it as a hosted service or remove its license keys.

In plain English

Context Mode is an MCP server, a small program that plugs into AI coding agents like Claude Code, Cursor, and a list of others, and changes how those agents handle large pieces of data. The README explains the core problem: every time an agent calls a tool, the raw response goes straight into the model's context window. A web page snapshot taken with Playwright might be 56 KB, twenty GitHub issues might be 59 KB, a single access log file might be 45 KB. After half an hour of this, the README says, 40% of the working memory has been spent on data the model is no longer using, and when the conversation has to compact itself, the agent loses track of what it was doing. The tool addresses this in four ways according to the README. First, sandbox tools run external commands and keep the raw output out of context, replacing it with a small summary, one stated figure is 315 KB becoming 5.4 KB, a 98% reduction. Second, session continuity is tracked in a SQLite database with full-text search, when the conversation is compacted, only the events the model needs are retrieved via BM25 ranking rather than dumping everything back in. Third, what the README calls Think in Code asks the agent to write a script that returns only the answer rather than reading every file. Fourth, the project deliberately does not impose a writing style on the model's replies, citing benchmarks where strict brevity rules hurt coding performance. Installation is grouped by platform. The README documents 15 of them. Claude Code is the easiest case: two slash commands add the plugin marketplace and install context-mode, after which a SessionStart hook injects the routing instructions automatically and a doctor command validates the setup. Platforms with hook support get fully automatic routing enforcement, the others need a one-time routing file copied into the project. The MCP server ships eleven tools. Six are sandbox tools for running code and indexing data: ctx_batch_execute, ctx_execute, ctx_execute_file, ctx_index, ctx_search, and ctx_fetch_and_index. Five meta-tools cover statistics, diagnostics, upgrades, purging old data, and insights. Slash commands surface the same functions inside the agent. The README opens with logos of companies whose teams the project claims as users and shows a 570-point Hacker News thread as social proof. The license is the Elastic License v2. The full README is longer than what was shown.

Copy-paste prompts

Prompt 1

Give me a 5-minute setup guide for installing context-mode in Claude Code using the plugin marketplace slash commands

Prompt 2

Show me how to call ctx_execute and ctx_index from an agent to fetch and search a 300 KB log file

Prompt 3

Explain what the SessionStart hook does in context-mode and how routing enforcement differs on platforms without hooks

Prompt 4

Walk me through using ctx_fetch_and_index to crawl a docs site and then ctx_search to retrieve answers

Prompt 5

How do I check context-mode is wired up correctly using the doctor slash command and read the stats meta tool

Frequently asked questions

What is context-mode?

MCP server that keeps large tool outputs out of an AI coding agent's context window by sandboxing commands and storing session events in a searchable SQLite database.

What language is context-mode written in?

Mainly TypeScript. The stack also includes TypeScript, MCP, SQLite.

Is context-mode actively maintained?

Maintained — commit in last 6 months (last push 2026-05-21).

What license does context-mode use?

Elastic License v2 lets you use and modify the code for free, but you cannot offer it as a hosted service or remove its license keys.

How hard is context-mode to set up?

Setup difficulty is rated moderate, with roughly 30min to a first successful run.

Who is context-mode for?

Mainly developer.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.