AI 工具AI TOOLS· CHAT-AGENT
cortexkit/magic-context
为AI编码代理提供无限上下文和自管理记忆的工具。A self-managing memory system that gives coding AI a lifelong context in a single session.
根据公开文档整理,未运行实测;费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.
能力CAPABILITIES
让AI助手记住跨会话的上下文
自动总结旧对话历史
用自然语言写入和检索记忆
为不同项目设置不同的记忆模型
关闭AI助手的自动压缩
Capture project decisions and architecture automatically
Recall past context with keyword or semantic search
Consolidate old memories to keep focus on current work
Manage context across multiple coding sessions
Keep your AI aware of your project's history
上手GET STARTED
npx @cortexkit/magic-context@latest setup选择与你的环境对应的方式。命令来自项目文档,未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.
使用限制LIMITATIONS
以下要求与风险来自文档静态检查,未执行项目代码;扫描没有命中,不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
未知Unknown
静态扫描STATIC SCAN
在 README、SKILL.md 和依赖清单中没有匹配到已知风险模式。No known risk patterns matched in the README, SKILL.md or dependency list.
安装脚本通过 curl 管道直接执行远程代码(curl -fsSL ... | bash),存在高风险:若脚本被篡改或中间人攻击,可能执行恶意命令。建议手动下载脚本审查后再运行,或使用 npx 方式安装。The installer downloads and runs a shell script from GitHub. This is a common pattern but carries risk — review the script before running if you're concerned about security.
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
+12.6%+12.6%
2.3k → 2.5k stars · 48 个快照2.3k → 2.5k stars · 48 snapshots
状态STATUS
持续活跃Active
质量 BQuality B
近7天有605次提交,项目迭代非常活跃,功能快速完善。2330 stars and 605 commits in the last week show active development
{
"agents": [
{
"agent": "opencode",
"evidence": "readme: ….npmjs.com/package/@cortexkit/opencode-magic-context\"><img src=\"http…"
}
],
"apiKey": null,
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 3,
"dev-tools": 1,
"indie-web": 0,
"skill-agent": 3,
"productivity": 3
},
"primary": "ai-tools",
"secondary": "chat-agent"
},
"localRuntime": "\"` or an `openai_compatible`/`ollama` embedding backend is configured. (`mem",
"skillMdTotal": 0,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 0,
"agent": 3,
"media": 0,
"design": 0,
"browser": 0,
"devtool": 0,
"security": 0,
"marketing": 0,
"productivity": 0
},
"classification": [],
"scannedSources": [
"readme"
],
"skillMdFetched": 0
}