开发者工具DEVELOPER TOOLS· CLI
snchimata/tokenfold
在本地无损压缩JSON和日志,减少LLM token消耗,降低API成本。Losslessly compress JSON logs and schemas to fit more tokens in your LLM context window — no data sent outside your network.
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
把JSON数据压缩到原来一半以下的token数
在本地无损压缩日志和结构,不联网
用一条命令把压缩后的内容还原成原始数据
让AI只保留你指定的关键信息,丢掉无关内容
把OpenAI格式的请求压缩后再发给上游
Compress JSON logs losslessly for LLM prompts
Reduce token usage without losing any data
Fit more structured data into context windows
Run compression entirely inside your own network
Use with any LLM through a local proxy
上手GET STARTED
npm install tokenfold@0.6.0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.
静态扫描未发现明显风险,但不代表安全A static scan found no obvious security risks, but that does not prove the software is safe.
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
+201.5%+201.5%
131 → 395 stars · 50 个快照131 → 395 stars · 50 snapshots
状态STATUS
持续活跃Active
质量 AQuality A
可以无损压缩JSON、日志和schema,节省LLM调用的token成本,实测30条记录从原始token压缩到500 token以内。Lossless compression — every byte can be recovered exactly
{
"agents": [
{
"agent": "cline",
"evidence": "tree: .clinerules/"
},
{
"agent": "claude-code",
"evidence": "readme: …fold init` currently supports Claude Code; Codex uses manual MCP regist…"
}
],
"apiKey": null,
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 4,
"dev-tools": 7,
"indie-web": 1,
"skill-agent": 3,
"productivity": 7
},
"primary": "dev-tools",
"secondary": "cli"
},
"localRuntime": "o repository checkout, model, GPU, or ML framework: ```bash python -m pi",
"skillMdTotal": 0,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 0,
"agent": 0,
"media": 0,
"design": 0,
"browser": 0,
"devtool": 2,
"security": 0,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "MCP topic + README",
"weight": 0.6
}
],
"scannedSources": [
"readme"
],
"skillMdFetched": 0
}