clew-code 0.4.3 → 0.4.5
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +239 -281
- package/dist/main.js +1709 -1709
- package/package.json +162 -161
package/README.md
CHANGED
|
@@ -1,292 +1,250 @@
|
|
|
1
|
-
<div align="center">
|
|
2
|
-
|
|
3
|
-
<img src="assets/clew-logo-long.png" alt="Clew Code" width="480" />
|
|
4
|
-
|
|
5
|
-
# Clew Code
|
|
6
|
-
|
|
7
|
-
**
|
|
8
|
-
|
|
9
|
-
A local-first coding CLI
|
|
10
|
-
|
|
11
|
-
[](https://github.com/ClewCode/ClewCode/stargazers)
|
|
12
|
-
[](https://github.com/ClewCode/ClewCode/releases)
|
|
13
|
-
[](https://www.npmjs.com/package/clew-code)
|
|
14
|
-
[](https://github.com/ClewCode/ClewCode/actions/workflows/ci.yml)
|
|
15
|
-
[](#license)
|
|
16
|
-
[](#install)
|
|
17
|
-
[](https://bun.sh)
|
|
18
|
-
|
|
19
|
-
[GitHub](https://github.com/ClewCode/ClewCode) · [Website](https://clew-code.org) · [
|
|
20
|
-
|
|
21
|
-
</div>
|
|
22
|
-
|
|
23
|
-
---
|
|
24
|
-
|
|
25
|
-
## What is Clew Code?
|
|
26
|
-
|
|
27
|
-
Clew Code is an AI coding agent that lives in your terminal.
|
|
28
|
-
|
|
29
|
-
It is built around three ideas:
|
|
30
|
-
|
|
31
|
-
- **Local-first.** Your code, memory, and configuration stay on your machine. Ships as a single Bun bundle with no required cloud backend.
|
|
32
|
-
- **It remembers.** A SQLite-backed memory system
|
|
33
|
-
- **It scales across machines.** Discover other Clew instances on your LAN, assign tasks, sync memory, and broadcast commands to a swarm.
|
|
34
|
-
|
|
35
|
-
---
|
|
36
|
-
|
|
37
|
-
## Install
|
|
38
|
-
|
|
39
|
-
###
|
|
40
|
-
|
|
41
|
-
|
|
42
|
-
|
|
43
|
-
|
|
44
|
-
|
|
45
|
-
|
|
46
|
-
|
|
47
|
-
|
|
48
|
-
|
|
49
|
-
|
|
50
|
-
|
|
51
|
-
```
|
|
52
|
-
|
|
53
|
-
|
|
54
|
-
|
|
55
|
-
|
|
56
|
-
|
|
57
|
-
|
|
58
|
-
|
|
59
|
-
|
|
60
|
-
|
|
61
|
-
|
|
62
|
-
|
|
63
|
-
|
|
64
|
-
|
|
65
|
-
|
|
66
|
-
|
|
67
|
-
|
|
68
|
-
|
|
69
|
-
|
|
70
|
-
|
|
71
|
-
|
|
72
|
-
|
|
73
|
-
|
|
74
|
-
|
|
75
|
-
|
|
76
|
-
|
|
77
|
-
|
|
78
|
-
|
|
79
|
-
|
|
80
|
-
|
|
81
|
-
|
|
82
|
-
|
|
83
|
-
|
|
84
|
-
|
|
85
|
-
|
|
86
|
-
|
|
87
|
-
|
|
88
|
-
|
|
89
|
-
|
|
90
|
-
|
|
91
|
-
|
|
92
|
-
|
|
93
|
-
|
|
94
|
-
|
|
95
|
-
|
|
96
|
-
|
|
97
|
-
|
|
98
|
-
|
|
99
|
-
#
|
|
100
|
-
|
|
101
|
-
|
|
102
|
-
#
|
|
103
|
-
|
|
104
|
-
```
|
|
105
|
-
|
|
106
|
-
Inside the REPL:
|
|
107
|
-
|
|
108
|
-
```text
|
|
109
|
-
❯ /model gpt-5.5 # switch provider/model mid-session
|
|
110
|
-
❯ /model ollama/llama3.3 # go fully local
|
|
111
|
-
❯ /status # provider, model, context usage
|
|
112
|
-
❯ /goal "tests pass" # track + verify task completion
|
|
113
|
-
❯ /memory dashboard # memory system status
|
|
114
|
-
❯ /peer discover # find Clew instances on the LAN
|
|
115
|
-
❯ /mcp list # connected MCP servers
|
|
116
|
-
❯ /help # list everything
|
|
117
|
-
```
|
|
118
|
-
|
|
119
|
-
---
|
|
120
|
-
|
|
121
|
-
## Features
|
|
122
|
-
|
|
123
|
-
### Multi-provider
|
|
124
|
-
**27 providers** — OpenAI, Google Gemini & Code Assist, DeepSeek, Groq, xAI (Grok), Mistral, Cohere, Perplexity, Cerebras, Moonshot (Kimi), Zhipu (GLM), NVIDIA NIM, OpenRouter, OpenCode, KiloCode, Sakana AI, Ollama, Together AI, Fireworks AI, Deep Infra, SiliconFlow, Hugging Face, Poe, DigitalOcean, Cline, and custom endpoints. Switch any time with `/model`. *(Anthropic models are reachable via OpenRouter or Cline.)*
|
|
125
|
-
|
|
126
|
-
### Memory system (MiMo-inspired)
|
|
127
|
-
A SQLite-backed memory store with importance ranking, confidence scoring, access tracking, and timeline logging. It auto-initializes and scans your project on first use, then injects a token-budgeted selection of memories (ranked by importance × recency × confidence) into the system prompt each turn. Durable facts are extracted automatically during context compaction, and **Dream** (7-day) + **Distill** (30-day) jobs consolidate memory over time. See it all in `/memory dashboard`.
|
|
128
|
-
|
|
129
|
-
### Peer-to-peer LAN swarm
|
|
130
|
-
Discover other Clew instances on the same machine (file registry) or across the LAN (UDP multicast). Assign tasks, set roles, and broadcast shell commands to every peer in parallel with `/peer swarm`. Memory syncs between peers on demand or on a cron. All endpoints are protected by a per-instance auth token, with a 10 MB request-body limit.
|
|
131
|
-
|
|
132
|
-
### Autonomous agent loop
|
|
133
|
-
A file-backed persistent task queue with lease-based concurrency, exponential-backoff retry, and dead-letter handling. A cron scheduler runs recurring jobs, up to 3 concurrent workers.
|
|
134
|
-
|
|
135
|
-
### Goals & verification
|
|
136
|
-
`/goal` tracks task completion with heuristic pre-checks (exit codes, test output, lint results), chained goals via `then`, and templates like `fix-build` and `green-tests`. When the agent declares a task done, an independent LLM verifier reviews the conversation against the goal and reports any gaps.
|
|
137
|
-
|
|
138
|
-
### 70+ built-in tools
|
|
139
|
-
Read, Write, Edit, Glob, Grep, Bash, WebSearch, WebFetch, Browser (Playwright), NotebookEdit, LSP, subagent dispatch (`Agent`), 17 LAN peer-coordination tools, MCP tools, `delegate` (exec/pty to external CLIs), and agent-driven memory curation.
|
|
140
|
-
|
|
141
|
-
### Extensible
|
|
142
|
-
- **MCP** — connect external tools over stdio, SSE (with OAuth), or in-process DirectConnect.
|
|
143
|
-
- **Skills, plugins, hooks** — extend without touching source. Skills via `SKILL.md`, plugins via manifest, and hooks at every lifecycle stage (PreToolUse, PostToolUse, PreBash, PostPrompt, PreAcceptEdit).
|
|
144
|
-
- **8 permission modes** — default, ask, plan, auto, acceptEdits, bypassPermissions, dontAsk, guardian, with granular allow/deny pattern rules.
|
|
1
|
+
<div align="center">
|
|
2
|
+
|
|
3
|
+
<img src="assets/clew-logo-long.png" alt="Clew Code" width="480" />
|
|
4
|
+
|
|
5
|
+
# Clew Code
|
|
6
|
+
|
|
7
|
+
**An open-source, multi-provider AI coding agent for the terminal.**
|
|
8
|
+
|
|
9
|
+
A reverse-engineered, local-first coding CLI inspired by Claude Code. It runs on your own hardware with your own API keys — no vendor lock-in.
|
|
10
|
+
|
|
11
|
+
[](https://github.com/ClewCode/ClewCode/stargazers)
|
|
12
|
+
[](https://github.com/ClewCode/ClewCode/releases)
|
|
13
|
+
[](https://www.npmjs.com/package/clew-code)
|
|
14
|
+
[](https://github.com/ClewCode/ClewCode/actions/workflows/ci.yml)
|
|
15
|
+
[](#license)
|
|
16
|
+
[](#install)
|
|
17
|
+
[](https://bun.sh)
|
|
18
|
+
|
|
19
|
+
[GitHub](https://github.com/ClewCode/ClewCode) · [Website](https://clew-code.org) · [Issues](https://github.com/ClewCode/ClewCode/issues)
|
|
20
|
+
|
|
21
|
+
</div>
|
|
22
|
+
|
|
23
|
+
---
|
|
24
|
+
|
|
25
|
+
## What is Clew Code?
|
|
26
|
+
|
|
27
|
+
Clew Code is an AI coding agent that lives in your terminal. It is **provider-agnostic** — bring an API key from OpenAI, Google, DeepSeek, Groq, OpenRouter, a local Ollama model, or any supported provider, and switch between them mid-session.
|
|
28
|
+
|
|
29
|
+
It is built around three ideas:
|
|
30
|
+
|
|
31
|
+
- **Local-first.** Your code, memory, and configuration stay on your machine. Ships as a single Bun bundle with no required cloud backend.
|
|
32
|
+
- **It remembers.** A SQLite-backed memory system stores decisions, preferences, and project context, then injects relevant information back into prompts.
|
|
33
|
+
- **It scales across machines.** Discover other Clew instances on your LAN, assign tasks, sync memory, and broadcast commands to a swarm.
|
|
34
|
+
|
|
35
|
+
---
|
|
36
|
+
|
|
37
|
+
## Install
|
|
38
|
+
|
|
39
|
+
### npm
|
|
40
|
+
|
|
41
|
+
```bash
|
|
42
|
+
npm install -g clew-code
|
|
43
|
+
```
|
|
44
|
+
|
|
45
|
+
### From source
|
|
46
|
+
|
|
47
|
+
```bash
|
|
48
|
+
git clone https://github.com/ClewCode/ClewCode.git
|
|
49
|
+
cd ClewCode
|
|
50
|
+
bun install && bun run build && bun run start
|
|
51
|
+
```
|
|
52
|
+
|
|
53
|
+
**Requirements:** [Bun](https://bun.sh) 1.3+, Git, and at least one provider API key.
|
|
54
|
+
|
|
55
|
+
<details>
|
|
56
|
+
<summary><b>Platform notes</b></summary>
|
|
57
|
+
|
|
58
|
+
- **macOS** — works out of the box (Apple Silicon & Intel).
|
|
59
|
+
- **Linux** — no special dependencies.
|
|
60
|
+
- **Windows** — requires Git Bash, WSL, or PowerShell.
|
|
61
|
+
</details>
|
|
62
|
+
|
|
63
|
+
---
|
|
64
|
+
|
|
65
|
+
## Quick start
|
|
66
|
+
|
|
67
|
+
```bash
|
|
68
|
+
# Launch in any project — pick a provider on first run
|
|
69
|
+
cd my-project
|
|
70
|
+
clew
|
|
71
|
+
```
|
|
72
|
+
|
|
73
|
+
Set a provider key via environment variable, or configure it inside the REPL:
|
|
74
|
+
|
|
75
|
+
```bash
|
|
76
|
+
export OPENAI_API_KEY=sk-...
|
|
77
|
+
export GOOGLE_API_KEY=...
|
|
78
|
+
export DEEPSEEK_API_KEY=...
|
|
79
|
+
export GROQ_API_KEY=...
|
|
80
|
+
export OPENROUTER_API_KEY=...
|
|
81
|
+
export OLLAMA_HOST=http://localhost:11434
|
|
82
|
+
```
|
|
83
|
+
|
|
84
|
+
```bash
|
|
85
|
+
# One-shot mode (pipe-friendly)
|
|
86
|
+
clew -p "summarize CHANGELOG.md"
|
|
87
|
+
|
|
88
|
+
# Resume your last session
|
|
89
|
+
clew --resume last
|
|
90
|
+
```
|
|
91
|
+
|
|
92
|
+
Inside the REPL:
|
|
93
|
+
|
|
94
|
+
```text
|
|
95
|
+
❯ /model gemini-2.5-flash # switch provider/model mid-session
|
|
96
|
+
❯ /model ollama/llama3.3 # go fully local
|
|
97
|
+
❯ /status # provider, model, context usage
|
|
98
|
+
❯ /goal "tests pass" # track + verify task completion
|
|
99
|
+
❯ /memory dashboard # memory system status
|
|
100
|
+
❯ /peer discover # find Clew instances on the LAN
|
|
101
|
+
❯ /mcp list # connected MCP servers
|
|
102
|
+
❯ /help # list everything
|
|
103
|
+
```
|
|
145
104
|
|
|
146
105
|
---
|
|
147
106
|
|
|
148
|
-
##
|
|
107
|
+
## Features
|
|
108
|
+
|
|
109
|
+
### Multi-provider
|
|
110
|
+
Supports OpenAI, Google Gemini & Code Assist, DeepSeek, Groq, xAI (Grok), Mistral, Cohere, Perplexity, Cerebras, Moonshot (Kimi), Zhipu (GLM), NVIDIA NIM, OpenRouter, OpenCode, KiloCode, Sakana AI, Ollama, Together AI, Fireworks AI, Deep Infra, SiliconFlow, Hugging Face, Poe, DigitalOcean, Cline, and custom endpoints. Switch any time with `/model`. Anthropic models are reachable via OpenRouter or Cline.
|
|
111
|
+
|
|
112
|
+
### Memory system
|
|
113
|
+
A SQLite-backed memory store with importance ranking, confidence scoring, and access tracking. It auto-initializes and scans your project on first use, then injects a token-budgeted selection of memories into the system prompt each turn. Durable facts are extracted during context compaction, and background jobs consolidate memory over time.
|
|
149
114
|
|
|
150
|
-
|
|
151
|
-
|
|
152
|
-
around `clew -p`, a `prepare`/`run` driver, prediction JSONL output, and optional
|
|
153
|
-
Docker harness execution.
|
|
115
|
+
### Peer-to-peer LAN swarm
|
|
116
|
+
Discover other Clew instances on the same machine or across the LAN. Assign tasks, set roles, and broadcast shell commands to every peer in parallel. Team memory sync with conflict resolution and delta uploads.
|
|
154
117
|
|
|
155
|
-
|
|
156
|
-
|
|
157
|
-
|
|
118
|
+
### Tools
|
|
119
|
+
Built-in tools for file I/O (Read, Write, Edit, Glob, Grep), shell commands (Bash), web (WebSearch, WebFetch, browser via Playwright), task tracking, LSP integration, subagent dispatch (`Agent`), LAN peer coordination, MCP tools, and agent-driven memory curation.
|
|
120
|
+
|
|
121
|
+
### Extensible
|
|
122
|
+
- **MCP** — connect external tools over stdio, SSE, or in-process DirectConnect.
|
|
123
|
+
- **Skills, plugins, hooks** — extend without touching source. Skills via `SKILL.md`, plugins via manifest, and lifecycle hooks (PreToolUse, PostToolUse, PreBash, PostPrompt, PreAcceptEdit).
|
|
124
|
+
- **Permission modes** — default, ask, plan, auto, acceptEdits, bypassPermissions, dontAsk, guardian.
|
|
125
|
+
|
|
126
|
+
### Other capabilities
|
|
127
|
+
- **Goals & verification** — track task completion with chained goals and independent LLM verification.
|
|
128
|
+
- **Autonomous agent loop** — persistent task queue with lease-based concurrency, retry, and dead-letter handling.
|
|
129
|
+
- **Context compaction** — recursive compression when the context window fills.
|
|
130
|
+
- **Checkpoints** — progress snapshots with a scratchpad for layered rebuild during compaction.
|
|
158
131
|
|
|
159
132
|
---
|
|
160
133
|
|
|
161
134
|
## Execution layers
|
|
162
135
|
|
|
163
136
|
Clew Code runs work at several layers, each for a different job:
|
|
164
|
-
|
|
165
|
-
| Layer | What it is | Use it for |
|
|
166
|
-
|-------|-----------|------------|
|
|
167
|
-
| **Agent** | An AI worker with a prompt, model, tools, and permissions. The main chat is an agent; custom ones live in `.clew/agents/*.md`. | The session itself. |
|
|
168
|
-
| **Subagent** | A short-lived child launched via the `Agent` tool
|
|
169
|
-
| **Teammate / Swarm** | A longer-lived agent with identity, mailbox, and task coordination. | Multi-turn collaboration between named workers. |
|
|
170
|
-
| **LAN Peer** | Another Clew instance on the same machine or network, reached via `/peer`. | Distributing work across machines. |
|
|
171
|
-
| **Process Peer** | A local worker that delegates to an external CLI
|
|
172
|
-
|
|
173
|
-
|
|
174
|
-
|
|
175
|
-
|
|
176
|
-
|
|
177
|
-
|
|
178
|
-
|
|
179
|
-
|
|
180
|
-
|
|
181
|
-
|
|
182
|
-
|
|
183
|
-
/
|
|
184
|
-
/
|
|
185
|
-
/
|
|
186
|
-
/
|
|
187
|
-
/
|
|
188
|
-
/
|
|
189
|
-
/
|
|
190
|
-
/
|
|
191
|
-
/
|
|
192
|
-
/
|
|
193
|
-
/
|
|
194
|
-
/
|
|
195
|
-
/
|
|
196
|
-
/
|
|
197
|
-
/
|
|
198
|
-
/
|
|
199
|
-
/
|
|
200
|
-
/
|
|
201
|
-
/
|
|
202
|
-
/
|
|
203
|
-
/
|
|
204
|
-
/
|
|
205
|
-
/
|
|
206
|
-
/
|
|
207
|
-
/
|
|
208
|
-
/
|
|
209
|
-
/
|
|
210
|
-
/
|
|
211
|
-
/
|
|
212
|
-
/
|
|
213
|
-
|
|
214
|
-
|
|
215
|
-
|
|
216
|
-
|
|
217
|
-
|
|
218
|
-
|
|
219
|
-
|
|
220
|
-
|
|
221
|
-
|
|
222
|
-
|
|
223
|
-
|
|
224
|
-
|
|
225
|
-
|
|
226
|
-
|
|
227
|
-
|
|
228
|
-
├──
|
|
229
|
-
├──
|
|
230
|
-
├──
|
|
231
|
-
├──
|
|
232
|
-
├──
|
|
233
|
-
│ ├──
|
|
234
|
-
│ ├──
|
|
235
|
-
│ ├──
|
|
236
|
-
│ ├──
|
|
237
|
-
│ ├──
|
|
238
|
-
│ ├──
|
|
239
|
-
│
|
|
240
|
-
|
|
241
|
-
|
|
242
|
-
├──
|
|
243
|
-
├──
|
|
244
|
-
|
|
245
|
-
|
|
246
|
-
|
|
247
|
-
|
|
248
|
-
|
|
249
|
-
|
|
250
|
-
|
|
251
|
-
|
|
252
|
-
|
|
253
|
-
|
|
254
|
-
|
|
255
|
-
|
|
256
|
-
bun
|
|
257
|
-
bun
|
|
258
|
-
bun
|
|
259
|
-
|
|
260
|
-
|
|
261
|
-
|
|
262
|
-
|
|
263
|
-
|
|
264
|
-
|
|
265
|
-
|
|
266
|
-
|
|
267
|
-
|
|
268
|
-
|
|
269
|
-
|
|
270
|
-
|
|
271
|
-
|
|
272
|
-
|
|
273
|
-
|
|
274
|
-
|
|
275
|
-
|
|
276
|
-
|
|
277
|
-
|
|
278
|
-
- Improve docs and examples
|
|
279
|
-
- Build a plugin or MCP server
|
|
280
|
-
- Improve Windows support
|
|
281
|
-
|
|
282
|
-
<a href="https://github.com/ClewCode/ClewCode/graphs/contributors">
|
|
283
|
-
<img src="https://contrib.rocks/image?repo=ClewCode/ClewCode" alt="Contributors" />
|
|
284
|
-
</a>
|
|
285
|
-
|
|
286
|
-
---
|
|
287
|
-
|
|
288
|
-
## License
|
|
289
|
-
|
|
290
|
-
See [LICENSE.md](LICENSE.md). The license covers only contributor-authored modifications and original additions; it does not grant rights to third-party software, models, or trademarks.
|
|
291
|
-
|
|
292
|
-
Full version history: [CHANGELOG.md](CHANGELOG.md).
|
|
137
|
+
|
|
138
|
+
| Layer | What it is | Use it for |
|
|
139
|
+
|-------|-----------|------------|
|
|
140
|
+
| **Agent** | An AI worker with a prompt, model, tools, and permissions. The main chat is an agent; custom ones live in `.clew/agents/*.md`. | The session itself. |
|
|
141
|
+
| **Subagent** | A short-lived child launched via the `Agent` tool. | Independent investigation, test triage, review. |
|
|
142
|
+
| **Teammate / Swarm** | A longer-lived agent with identity, mailbox, and task coordination. | Multi-turn collaboration between named workers. |
|
|
143
|
+
| **LAN Peer** | Another Clew instance on the same machine or network, reached via `/peer`. | Distributing work across machines. |
|
|
144
|
+
| **Process Peer** | A local worker that delegates to an external CLI via `exec`/`pty`. | Running another coding tool as a subprocess. |
|
|
145
|
+
|
|
146
|
+
---
|
|
147
|
+
|
|
148
|
+
## Commands
|
|
149
|
+
|
|
150
|
+
<details>
|
|
151
|
+
<summary><strong>Slash commands</strong></summary>
|
|
152
|
+
|
|
153
|
+
```
|
|
154
|
+
/model Switch provider or model
|
|
155
|
+
/status Provider, session, context info
|
|
156
|
+
/doctor Diagnostics
|
|
157
|
+
/context Active context usage
|
|
158
|
+
/compact Compress history + extract memories
|
|
159
|
+
/goal Track and verify task completion
|
|
160
|
+
/memory Memory: init, scan, rebuild, recall, feedback, dashboard, search
|
|
161
|
+
/peer LAN peers: discover, send, swarm, dashboard, memory sync
|
|
162
|
+
/daemon Autonomous daemon dashboard
|
|
163
|
+
/task Scheduled tasks
|
|
164
|
+
/mcp MCP server management
|
|
165
|
+
/plugin Plugin and hook management
|
|
166
|
+
/skills List and manage skills
|
|
167
|
+
/code-review Review changed files for bugs
|
|
168
|
+
/simplify Cleanup-focused review
|
|
169
|
+
/guardian Auto-review mode using a secondary LLM
|
|
170
|
+
/approve Override guardian denials
|
|
171
|
+
/pr GitHub PR lifecycle
|
|
172
|
+
/plan Plan mode
|
|
173
|
+
/fork Fork conversation into a new session
|
|
174
|
+
/rewind Undo last response
|
|
175
|
+
/effort Set reasoning effort
|
|
176
|
+
/stats Session statistics
|
|
177
|
+
/voice Voice input
|
|
178
|
+
/remote WebSocket remote control
|
|
179
|
+
/bridge Bridge mode config
|
|
180
|
+
/session Session management
|
|
181
|
+
/theme Theme switcher
|
|
182
|
+
/vim Vim keybindings
|
|
183
|
+
/login Sign in via Clew Gateway
|
|
184
|
+
/logout Sign out
|
|
185
|
+
/upgrade Check for updates
|
|
186
|
+
```
|
|
187
|
+
|
|
188
|
+
</details>
|
|
189
|
+
|
|
190
|
+
---
|
|
191
|
+
|
|
192
|
+
## Project layout
|
|
193
|
+
|
|
194
|
+
<details>
|
|
195
|
+
<summary><strong>src/ — single-entry Bun bundle</strong></summary>
|
|
196
|
+
|
|
197
|
+
```
|
|
198
|
+
src/
|
|
199
|
+
├── main.tsx # Entry point
|
|
200
|
+
├── QueryEngine.ts # Core query + tool loop
|
|
201
|
+
├── commands/ # Slash command implementations
|
|
202
|
+
├── tools/ # Built-in tools
|
|
203
|
+
├── services/
|
|
204
|
+
│ ├── ai/ # Provider manager + adapters
|
|
205
|
+
│ ├── mcp/ # MCP client + auth + transports
|
|
206
|
+
│ ├── plugins/ # Plugin hooks + marketplace
|
|
207
|
+
│ ├── autonomous/ # Agent loop + task queue + cron
|
|
208
|
+
│ ├── search/ # Web search providers
|
|
209
|
+
│ ├── checkpoint/ # Structured progress checkpoints
|
|
210
|
+
│ ├── goal/ # Goal evaluation and verification
|
|
211
|
+
│ ├── longTermMemory/ # Memory consolidation
|
|
212
|
+
│ └── compact/ # Context compression
|
|
213
|
+
├── peer/ # PeerServer + PeerDiscovery
|
|
214
|
+
├── memory/ # MemoryDB + scanner + feedback
|
|
215
|
+
├── bridge/ # WebSocket bridge + relay
|
|
216
|
+
├── components/ # Ink terminal UI
|
|
217
|
+
└── hooks/ # React hooks
|
|
218
|
+
```
|
|
219
|
+
|
|
220
|
+
</details>
|
|
221
|
+
|
|
222
|
+
---
|
|
223
|
+
|
|
224
|
+
## Development
|
|
225
|
+
|
|
226
|
+
```bash
|
|
227
|
+
bun run dev # Live reload
|
|
228
|
+
bun run build # Build to dist/
|
|
229
|
+
bun test # Run tests
|
|
230
|
+
bun x tsc --noEmit # Type-check
|
|
231
|
+
bun run check:ci # Lint + format check (Biome CI)
|
|
232
|
+
```
|
|
233
|
+
|
|
234
|
+
---
|
|
235
|
+
|
|
236
|
+
## Contributing
|
|
237
|
+
|
|
238
|
+
Contributions are welcome. Please read [CONTRIBUTING.md](CONTRIBUTING.md), [CODE_OF_CONDUCT.md](CODE_OF_CONDUCT.md), and [SECURITY.md](SECURITY.md) first.
|
|
239
|
+
|
|
240
|
+
<a href="https://github.com/ClewCode/ClewCode/graphs/contributors">
|
|
241
|
+
<img src="https://contrib.rocks/image?repo=ClewCode/ClewCode" alt="Contributors" />
|
|
242
|
+
</a>
|
|
243
|
+
|
|
244
|
+
---
|
|
245
|
+
|
|
246
|
+
## License
|
|
247
|
+
|
|
248
|
+
See [LICENSE.md](LICENSE.md).
|
|
249
|
+
|
|
250
|
+
Full version history: [CHANGELOG.md](CHANGELOG.md).
|