免費 / 開源Runs parallel CLI coding agents in isolated worktrees, lacking dedicated context compression and cost routing tools.
| 面向/指標 | ![]() | |
|---|---|---|
| 官方網域 | caveman.so | promptr.dev |
| 定價模式 | 免費增值、需聯絡報價 | Pay-as-you-go |
| 每月造訪次數 | 17.18萬 (171,826) | 0 (0) |
| 月流量變化量 | -3.16萬 (-15.5%) | 0 (0%) |
| 主要市場與市佔 | 🇺🇸 美國 (30%) | 🌐 全球 (—) |
| 每月直接造訪 | 6.42萬 | 0 |
| 使用者評分 | 4.7 | 3.6 |
| 支援平台 | 網站 | 網站 |

用可還原的上下文壓縮與智慧模型路由,降低 AI Agent 權杖成本
用一次 REST 呼叫壓縮 LLM 提示詞,降低 token 成本
把提示詞送到單一 REST 端點,即可取回純文字的精簡版本,直接交給模型使用。
供應商表示 LLM 輸入成本最多可降低 40%,並以範例展示某提示詞減少 45%。
提供 curl、Python、JavaScript、C# 的複製即用範例,整合只需數分鐘而非數天。
用標籤包住段落,即可將其排除在壓縮之外,或為該區塊指定特定壓縮比例。
免費 / 開源Runs parallel CLI coding agents in isolated worktrees, lacking dedicated context compression and cost routing tools.
免費 / 開源Unsloth is an open-source toolkit for running and training large language models locally. It provides faster, more memory-efficient fine-tuning, a local chat and agent environment with browser use, image and video generation, and an OpenAI-compatible API your existing tools can connect to.
免費 / 開源Unsloth is an open-source toolkit for running and training large language models locally. It provides faster, more memory-efficient fine-tuning, a local chat and agent environment with browser use, image and video generation, and an OpenAI-compatible API your existing tools can connect to.

專項更強為程式碼編寫代理提供企業級上下文引擎,但缺乏開源 Token 壓縮與自訂模型路由功能。
專項更強為程式碼編寫代理提供企業級上下文引擎,但缺乏開源 Token 壓縮與自訂模型路由功能。

免費 / 開源Provides an open-source Python framework for building model-agnostic agents without built-in context compression.
免費 / 開源Honcho is an open-source memory layer for AI agents. It ingests messages, indexes them, and runs background reasoning so agents can recall who a user is, what happened before, and what to do next — across sessions, tools, and machines.
建立具備權限意識的上下文圖譜並將任務路由至模型,不過主要針對企業級代理工作流程。

專項更強提供企業級 LLM 閘道器與監控工具,但較少著墨於本地上下文壓縮與代理路由。
免費 / 開源Executes language model instructions locally via terminal sandbox, without built-in token optimization or model routing.
免費 / 開源Executes language model instructions locally via terminal sandbox, without built-in token optimization or model routing.

免費 / 開源Serves as an open-source workspace for testing and deploying agents, rather than optimizing token costs and routing.