R
Redskull-127/lucid
One shared dream for every Claude agent: live plan, evidence-backed decision log and file claims for the…
更新 2026-11-18
在 GitHub 查看 ↗链接已于 2026-11-17 核查 · HTTP 200 · 打开的是厂商自己的官网
- ★ 数取值
- 0 ★ · Redskull-127/lucid · 取自 GitHub 搜索 API · (2026-11-19 20:00:48 核对)
- 来源明细
- 从该仓库的 GitHub 页面直接读取 · 条目类型:开源项目
- 收录与活跃
- 收录于 2026-11-17 · 最近见到 2026-11-20 · 共见到 4 次 · 被 2 个来源列出
- 评分构成
- 综合分 203 · 2 个来源 · repo
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: 开源项目。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
Redskull-127/lucid;我们收录于 2026-11-17;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 →
lucid
以下摘录自该仓库的 README(片段)
One shared dream for every Claude.
A live plan, an evidence-backed memory and file claims shared by the lead agent, its subagents and Agent-Teams teammates.
Change the plan partway through and every running worker sees the change before its next action.
Install ·
How it works ·
Benchmark ·
Commands ·
Real run ·
Limits
## 🌙 The problem
You build a feature with several Claude agents working at once, then change your mind partway through. Things go wrong:
| Symptom | Why it happens |
| 🧭 Plan drift | Workers that are already running still follow the plan they were spawned with. Nothing tells them it changed. |
| 📉 Lossy handoffs | A subagent's summary leaves out the why, and leaves out the "we tried X, it broke". |
| 🔁 Repeated work | Every worker re-reads and re-searches the same code. |
| 🫥 Compaction amnesia | Decisions disappear when the conversation is compacted and in new sessions. |
| 💥 Overwritten work | Two agents edit the same file and one loses its changes. |
## ✨ What lucid does
lucid gives every agent in the project one shared memory, the dream, kept as plain files in .lucid/:
| File | What it holds |
| plan.md | The live plan. When anyone edits it, every running agent gets the diff before its next tool call. |
| log.jsonl | An append-only memory: decisions (with why), facts (with path:line evidence), dead ends, blockers and file claims. |
| digest.md | A consolidated summary, written when you run /lucid:dream. |
The memory is wired in through hooks, so agents can't forget to check it. Agents only add to the log and never rewrite it. A fact whose cited code has changed is flagged ⚠stale, so shared memory doesn't spread outdated claims.
## 🔭 How it works
| Hook | What it does |
| SessionStart (also after /compact) · SubagentStart | Injects the plan, the live memory and active claims, within a fixed budget. Subagents and Agent-Teams teammates start with the full shared context instead of a one-paragraph brief. |
| UserPromptSubmit · PreToolUse | Injects only what other agents wrote since you last looked. When nothing changed it injects nothing and costs no tokens. |
| PreToolUse on edits | 🔒 Blocks a write to a file another active agent has claimed, whether it goes through Edit/Write or through Bash (>, sed -i, cp/mv, scripts that open(…, 'w')). |
| PreToolUse on Bash | Adds the calling agent's real id to every lucid command, so every entry records who wrote it and agents never have to manage ids. |
| SubagentStop · TaskCompleted | Asks once for notes from an agent that edited files but logged nothing. A stopping subagent's claims are released. |
| Stop · SessionEnd | Releases a session's claims when its turn or the session ends, so an idle agent never blocks others. |
| UserPromptSubmit while workers are busy | Reminds the lead to write a chat change of plan into plan.md first, so running workers get it and it survives /compact. |
> lucid stays inactive until a project opts in with lucid init. In every other project a tiny shell guard checks for .lucid/ and exits without starting Python. It works from repo subfolders and git worktrees, which share the main checkout's dream.
## 📊 Benchmark
A live plan, an evidence-backed memory and file claims shared by the lead agent, its subagents and Agent-Teams teammates.
Change the plan partway through and every running worker sees the change before its next action.
Install ·
How it works ·
Benchmark ·
Commands ·
Real run ·
Limits
## 🌙 The problem
You build a feature with several Claude agents working at once, then change your mind partway through. Things go wrong:
| Symptom | Why it happens |
| 🧭 Plan drift | Workers that are already running still follow the plan they were spawned with. Nothing tells them it changed. |
| 📉 Lossy handoffs | A subagent's summary leaves out the why, and leaves out the "we tried X, it broke". |
| 🔁 Repeated work | Every worker re-reads and re-searches the same code. |
| 🫥 Compaction amnesia | Decisions disappear when the conversation is compacted and in new sessions. |
| 💥 Overwritten work | Two agents edit the same file and one loses its changes. |
## ✨ What lucid does
lucid gives every agent in the project one shared memory, the dream, kept as plain files in .lucid/:
| File | What it holds |
| plan.md | The live plan. When anyone edits it, every running agent gets the diff before its next tool call. |
| log.jsonl | An append-only memory: decisions (with why), facts (with path:line evidence), dead ends, blockers and file claims. |
| digest.md | A consolidated summary, written when you run /lucid:dream. |
The memory is wired in through hooks, so agents can't forget to check it. Agents only add to the log and never rewrite it. A fact whose cited code has changed is flagged ⚠stale, so shared memory doesn't spread outdated claims.
## 🔭 How it works
| Hook | What it does |
| SessionStart (also after /compact) · SubagentStart | Injects the plan, the live memory and active claims, within a fixed budget. Subagents and Agent-Teams teammates start with the full shared context instead of a one-paragraph brief. |
| UserPromptSubmit · PreToolUse | Injects only what other agents wrote since you last looked. When nothing changed it injects nothing and costs no tokens. |
| PreToolUse on edits | 🔒 Blocks a write to a file another active agent has claimed, whether it goes through Edit/Write or through Bash (>, sed -i, cp/mv, scripts that open(…, 'w')). |
| PreToolUse on Bash | Adds the calling agent's real id to every lucid command, so every entry records who wrote it and agents never have to manage ids. |
| SubagentStop · TaskCompleted | Asks once for notes from an agent that edited files but logged nothing. A stopping subagent's claims are released. |
| Stop · SessionEnd | Releases a session's claims when its turn or the session ends, so an idle agent never blocks others. |
| UserPromptSubmit while workers are busy | Reminds the lead to write a chat change of plan into plan.md first, so running workers get it and it survives /compact. |
> lucid stays inactive until a project opts in with lucid init. In every other project a tiny shell guard checks for .lucid/ and exits without starting Python. It works from repo subfolders and git worktrees, which share the main checkout's dream.
## 📊 Benchmark
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/redskull-127-lucid/)
- 来源
- github · https://github.com/Redskull-127/lucid
- 按领域浏览
- 开源项目
- 收录来源
- 2 个独立来源
- 收录于
- 今天
更多条目
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。