Repolode
제출하기
mksglu

mksglu/context-mode

MCP server for AI coding agents that keeps raw tool output out of the context window and persists session state across compaction.

GitHub에서 보기웹사이트
스타
30,905
포크
2,302
열린 이슈
356
마지막 커밋
2시간 전

어떤 프로젝트인가요?

Context Mode addresses the context-window problem that AI coding agents hit when MCP tools return large raw outputs such as browser snapshots, issue lists or log files. It runs tool work inside a sandbox so only the final result enters the conversation, and the project reports a 98% reduction on a 315 KB example.

It also tracks session events such as file edits, git operations, tasks, errors and user decisions in SQLite. Events are indexed with FTS5 and retrieved with BM25 search, so after the conversation compacts the agent can resume with the relevant state. Sessions that are not continued are cleared at the next start.

The project is delivered as an MCP server and is wired into many clients through plugins, hooks and config files, including Claude Code, Gemini CLI, VS Code Copilot, Cursor, OpenCode, Codex CLI and OpenClaw.

핵심 기능

  • 01Runs tool output in a sandbox so raw data stays out of the context window.
  • 02Stores session events in SQLite and restores relevant ones after compaction.
  • 03Searches indexed content with FTS5 and BM25 ranking.
  • 04Provides ctx_execute and related tools for running scripts that return only results.
  • 05Uses platform hooks to route tool calls across supported AI coding clients.

활용 사례

  • Long coding sessions where MCP tools such as browser or issue fetchers flood the context.
  • Analyzing many source files by having the agent write a script that outputs only the summary.
  • Resuming work after the agent compacts its conversation without re-reading prior state.

토픽

#mcp#ai-agent#context-window#claude-code#coding-assistant#sqlite#llm-tools#antigravity#claude#claude-code-hooks

자주 묻는 질문

context-mode은(는) 무엇인가요?
MCP server for AI coding agents that keeps raw tool output out of the context window and persists session state across compaction. Context Mode addresses the context-window problem that AI coding agents hit when MCP tools return large raw outputs such as browser snapshots, issue lists or log files. It runs tool work inside a sandbox so only the final result enters the conversation, and the project reports a 98% reduction on a 315 KB example.
context-mode은(는) 무료로 사용할 수 있나요? 라이선스는 무엇인가요?
context-mode은(는) Other 라이선스의 오픈소스입니다. 상업용 제품에 사용하기 전에 라이선스 조건을 확인하세요.
context-mode은(는) 아직 유지보수되고 있나요?
활발히 유지보수 중. context-mode의 마지막 커밋은 2026년 10월 19일입니다.
context-mode은(는) 어디에 사용할 수 있나요?
Long coding sessions where MCP tools such as browser or issue fetchers flood the context. Analyzing many source files by having the agent write a script that outputs only the summary. Resuming work after the agent compacts its conversation without re-reading prior state.
context-mode은(는) 어디서 받을 수 있나요?
소스 코드와 설치 방법은 GitHub에 있습니다: https://github.com/mksglu/context-mode

요약은 프로젝트 README를 바탕으로 AI가 작성했습니다. GitHub 통계는 매일 갱신됩니다.

관련 프로젝트