L
LuminariSoftwares/context-guardian
Status: active development -- changelog
★ 2·更新 2026-11-12
在 GitHub 查看 ↗直链 · 无中转页
我们没有可直接复制的安装命令,也没有公开的远端端点,所以不出配置。上面那条命令仅供参考,不是我们能担保的可复制命令——编一条出来比不给更糟。 各客户端的接法 →
- ★ 数取值
- 2 ★ · LuminariSoftwares/context-guardian · 取自 GitHub 搜索 API · (2026-11-19 20:00:48 核对)
- 来源明细
- 收录自 punkpeye/awesome-mcp-servers 榜单(我们从中收集的条目之一) · 条目类型:MCP 服务
- 收录与活跃
- 收录于 2026-11-18 · 最近见到 2026-11-20 · 共见到 3 次 · 被 3 个来源列出
- 评分构成
- 综合分 300 · 2 ★ · 3 个来源 · mcp
常见问题(答案都来自我们的记录)
它适合谁 / 用来做什么?
我们把它归在这些标签下: MCP 服务。标签来自条目自身,不是我们强加的分类。
谁维护它、还在更新吗?
仓库
LuminariSoftwares/context-guardian;我们收录于 2026-11-18;最近见到 2026-11-20。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。README 原文(英文,未翻译) · 在 GitHub 读完整 README →
Context Guardian
以下摘录自该仓库的 README(片段)
Status: active development -- changelog
mcp-name: io.github.LuminariSoftwares/context-guardian
A 40-turn session: 1,130,722 tokens sent upstream without it, 161,141 with it.
A compaction proxy for OpenAI-compatible local backends that fails open, so a long session stops dying at the context limit.
https://github.com/user-attachments/assets/1d1d63e9-4e2f-446e-8111-ae56a5a82f7f
## Quick start (60 seconds)
Local model CLI, through the proxy:
bash
pip install context-guardian && context-guardian # proxy on :8786 in front of Ollama on :11434; set OPENAI_BASE_URL=http://localhost:8786/v1
context-guardian-doctor # second terminal: checks the install and the running proxy, prints a fix: line for anything wrong
With an AI agent: paste one line, "Install context-guardian (docs: https://raw.githubusercontent.com/LuminariSoftwares/context-guardian/main/llms.txt) and point my client at it". llms.txt is the whole install, configure, recall and limits story in one short file an agent can read.
Another backend or window: see examples/ or Configure. Your client's settings: Point your client at the proxy. After a compaction, context-guardian-recall " " searches the archived originals (the summary the model receives names the exact command and the MCP tools).
DeepSeek Harness: dsh plugin --profile web add dsh-context-guardian, then npm run setup -- --apply in the installed package. Full steps: Install both.
Claude Code:
bash
pip install context-guardian
context-guardian-claude-code install # prints the hooks and the claude mcp add command; changes nothing
context-guardian-claude-code install --apply # backs up ~/.claude/settings.json, merges the hooks, prints the diff
claude mcp add --scope user --transport stdio context-guardian -- uvx context-guardian mcp
Details: Claude Code.
## Proof
bash
python scripts/bench_proxy.py --turns 40 --seed 1
text
turns=40 tokens_before=1130722 tokens_after=161141 compactions=27
Run 2026-11-05 on v0.15.0, Python 3.11, against a stub upstream.
text
623 passed, 1 warning in 106.22s (0:01:46)
python -m pytest -q, run 2026-11-05.
The bench runs against a stub upstream, not a real model; the token figures are the same on any machine. Fails open. If a summary fails, comes back empty or anything in the proxy raises, the request goes upstream exactly as your client sent it. Ollama (daily use) and DeepSeek Harness 0.1.2-alpha.2 are tested; the other backends and clients in Compatibility are configured from their documentation and marked untested.
Quick start ·
Prove it ·
Client settings ·
Claude Code ·
DeepSeek Harness ·
Recall ·
MCP server ·
Configure ·
Limits ·
Your data ·
Troubleshooting ·
Changelog
What it does. When a conversation is about to outgrow the model's context window, Context Guardian summarises the older turns, keeps the recent ones verbatim and forwards a request that fits. Everything it folds away is archived on disk, sealed in a hash chain you can verify, and indexed so a model can skim it in a few hundred tokens and open only what it needs. It runs on your machine, with no telemetry: nothing leaves it except the requests you were already sending to your own backend, and one cached PyPI version check you can turn off.
mcp-name: io.github.LuminariSoftwares/context-guardian
A 40-turn session: 1,130,722 tokens sent upstream without it, 161,141 with it.
A compaction proxy for OpenAI-compatible local backends that fails open, so a long session stops dying at the context limit.
https://github.com/user-attachments/assets/1d1d63e9-4e2f-446e-8111-ae56a5a82f7f
## Quick start (60 seconds)
Local model CLI, through the proxy:
bash
pip install context-guardian && context-guardian # proxy on :8786 in front of Ollama on :11434; set OPENAI_BASE_URL=http://localhost:8786/v1
context-guardian-doctor # second terminal: checks the install and the running proxy, prints a fix: line for anything wrong
With an AI agent: paste one line, "Install context-guardian (docs: https://raw.githubusercontent.com/LuminariSoftwares/context-guardian/main/llms.txt) and point my client at it". llms.txt is the whole install, configure, recall and limits story in one short file an agent can read.
Another backend or window: see examples/ or Configure. Your client's settings: Point your client at the proxy. After a compaction, context-guardian-recall " " searches the archived originals (the summary the model receives names the exact command and the MCP tools).
DeepSeek Harness: dsh plugin --profile web add dsh-context-guardian, then npm run setup -- --apply in the installed package. Full steps: Install both.
Claude Code:
bash
pip install context-guardian
context-guardian-claude-code install # prints the hooks and the claude mcp add command; changes nothing
context-guardian-claude-code install --apply # backs up ~/.claude/settings.json, merges the hooks, prints the diff
claude mcp add --scope user --transport stdio context-guardian -- uvx context-guardian mcp
Details: Claude Code.
## Proof
bash
python scripts/bench_proxy.py --turns 40 --seed 1
text
turns=40 tokens_before=1130722 tokens_after=161141 compactions=27
Run 2026-11-05 on v0.15.0, Python 3.11, against a stub upstream.
text
623 passed, 1 warning in 106.22s (0:01:46)
python -m pytest -q, run 2026-11-05.
The bench runs against a stub upstream, not a real model; the token figures are the same on any machine. Fails open. If a summary fails, comes back empty or anything in the proxy raises, the request goes upstream exactly as your client sent it. Ollama (daily use) and DeepSeek Harness 0.1.2-alpha.2 are tested; the other backends and clients in Compatibility are configured from their documentation and marked untested.
Quick start ·
Prove it ·
Client settings ·
Claude Code ·
DeepSeek Harness ·
Recall ·
MCP server ·
Configure ·
Limits ·
Your data ·
Troubleshooting ·
Changelog
What it does. When a conversation is about to outgrow the model's context window, Context Guardian summarises the older turns, keeps the recent ones verbatim and forwards a request that fits. Everything it folds away is archived on disk, sealed in a hash chain you can verify, and indexed so a model can skim it in a few hundred tokens and open only what it needs. It runs on your machine, with no telemetry: nothing leaves it except the requests you were already sending to your own backend, and one cached PyPI version check you can turn off.
收录徽章(可选)
想把收录标记放进 README 就复制这行,可选,不影响收录。
[](https://anclum.com/zh/s/luminarisoftwares-context-guardian/)
- 来源
- awesome · https://github.com/LuminariSoftwares/context-guardian
- 按领域浏览
- MCP 服务
- Traction
- 2 ★
- 收录来源
- 3 个独立来源
- 收录于
- 今天
更多 MCP 服务器
所属领域与标签
每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。