agent-recall-mcp 3.2.1 → 3.2.2
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 +131 -254
- package/dist/index.js +1 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -1,222 +1,167 @@
|
|
|
1
1
|
<p align="center">
|
|
2
|
-
<h1 align="center">
|
|
3
|
-
<p align="center"><strong>
|
|
2
|
+
<h1 align="center">AgentRecall</h1>
|
|
3
|
+
<p align="center"><strong>The Intelligent Distance Protocol for AI Agents</strong></p>
|
|
4
|
+
<p align="center">Minimize information loss between human and AI — across every session, every agent, every project.</p>
|
|
4
5
|
</p>
|
|
5
6
|
|
|
6
7
|
<p align="center">
|
|
7
8
|
<a href="https://www.npmjs.com/package/agent-recall-mcp"><img src="https://img.shields.io/npm/v/agent-recall-mcp?style=flat-square&color=5D34F2" alt="npm"></a>
|
|
8
9
|
<a href="https://github.com/NovadaLabs/AgentRecall/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-MIT-brightgreen?style=flat-square" alt="License"></a>
|
|
9
|
-
<img src="https://img.shields.io/badge/MCP-12_tools-orange?style=flat-square" alt="
|
|
10
|
-
<img src="https://img.shields.io/badge/
|
|
10
|
+
<img src="https://img.shields.io/badge/MCP-12_tools-orange?style=flat-square" alt="Tools">
|
|
11
|
+
<img src="https://img.shields.io/badge/protocol-Intelligent_Distance-5B2D8E?style=flat-square" alt="Protocol">
|
|
11
12
|
<img src="https://img.shields.io/badge/cloud-zero-blue?style=flat-square" alt="Zero Cloud">
|
|
12
13
|
</p>
|
|
13
14
|
|
|
14
|
-
<p align="center">
|
|
15
|
-
MCP server for persistent agent memory — session journals, structured JSON state,<br>
|
|
16
|
-
Think-Execute-Reflect quality loops, cache-aware cold start, and alignment detection.<br>
|
|
17
|
-
Works with <strong>Claude Code, Cursor, VS Code Copilot, Windsurf, Claude Desktop</strong>, and any MCP client.
|
|
18
|
-
</p>
|
|
19
|
-
|
|
20
|
-
<p align="center"><strong>Zero cloud. Zero telemetry. All data stays on your machine.</strong></p>
|
|
21
|
-
|
|
22
15
|
---
|
|
23
16
|
|
|
24
|
-
## The Core Idea
|
|
17
|
+
## Intelligent Distance — The Core Idea
|
|
25
18
|
|
|
26
19
|
> *"The gap between human intelligence and AI intelligence is structural and permanent — not a temporary technology problem."*
|
|
27
20
|
|
|
28
|
-
Humans
|
|
21
|
+
Humans are **born** (embodied experience, emotion, survival pressure). Machines are **made** (rules, deterministic). AI is **trained** (statistical co-occurrence over data). Three different cognitive origins produce three different ways of understanding the world. This gap will not close as AI improves — because the difference is in **origin**, not capability.
|
|
29
22
|
|
|
30
|
-
|
|
31
|
-
- When a human says "done means identical," the agent thinks "close enough"
|
|
32
|
-
- When a human gives scattered instructions, the agent picks one and ignores the rest
|
|
23
|
+
**The conventional approach:** make AI more human-like → close the gap.
|
|
33
24
|
|
|
34
|
-
**
|
|
25
|
+
**The Intelligent Distance approach:** accept the gap as permanent → design a **protocol** that minimizes information loss when translating between the two intelligence types.
|
|
35
26
|
|
|
36
|
-
|
|
27
|
+
```
|
|
28
|
+
Human says: "click all"
|
|
29
|
+
Agent hears: "click the main things"
|
|
30
|
+
Gap: "all" ≠ "main things"
|
|
37
31
|
|
|
38
|
-
|
|
39
|
-
|
|
40
|
-
|
|
41
|
-
| Agent misunderstands human intent | `alignment_check` | Records confidence + assumptions → human corrects before work starts |
|
|
42
|
-
| Agent contradicts a prior decision | `nudge` | Detects contradiction → surfaces it before damage is done |
|
|
43
|
-
| Agent says "done" but human disagrees | Think-Execute-Reflect loop | Structured quality scoring with COUNTS, not feelings |
|
|
44
|
-
| Agent builds from imagination, not data | `journal_state` (JSON) | Transfers structured state agent-to-agent — no prose interpretation |
|
|
45
|
-
| Agent repeats the same mistake | Failures section + `context_synthesize` | Patterns detected across sessions → promoted to permanent memory |
|
|
32
|
+
Human says: "done means identical"
|
|
33
|
+
Agent thinks: "close enough"
|
|
34
|
+
Gap: "identical" ≠ "close enough"
|
|
46
35
|
|
|
47
|
-
|
|
36
|
+
Human gives: scattered, non-linear instructions
|
|
37
|
+
Agent picks: one instruction, ignores the rest
|
|
38
|
+
Gap: the connective tissue between points is lost
|
|
39
|
+
```
|
|
40
|
+
|
|
41
|
+
**AgentRecall doesn't try to close this gap. It builds the protocol to navigate it.**
|
|
48
42
|
|
|
49
43
|
---
|
|
50
44
|
|
|
51
|
-
##
|
|
45
|
+
## How AgentRecall Bridges the Gap
|
|
52
46
|
|
|
53
|
-
|
|
|
54
|
-
|
|
55
|
-
| Agent forgets
|
|
56
|
-
| Agent
|
|
57
|
-
| Agent
|
|
58
|
-
|
|
|
59
|
-
|
|
|
60
|
-
|
|
|
47
|
+
| Intelligent Distance Gap | AgentRecall Tool | What It Does |
|
|
48
|
+
|--------------------------|-----------------|-------------|
|
|
49
|
+
| Agent forgets what human said yesterday | `journal_read` + `journal_cold_start` | Persistent memory — 3-layer, cache-aware |
|
|
50
|
+
| Agent misunderstands human intent | `alignment_check` | Records confidence + assumptions → human corrects BEFORE work |
|
|
51
|
+
| Agent contradicts a prior decision | `nudge` | Detects contradiction → surfaces it BEFORE damage |
|
|
52
|
+
| Agent says "done" but human disagrees | Think-Execute-Reflect loop | Quality scoring with COUNTS ("built 11 pages, 35 tabs"), not feelings ("went well") |
|
|
53
|
+
| Agent builds from imagination, not data | `journal_state` (JSON) | Structured state transfers agent-to-agent — no prose interpretation |
|
|
54
|
+
| Agent repeats the same mistake | Failures section + `context_synthesize` | Cross-session pattern detection → promoted to permanent memory |
|
|
55
|
+
| Next agent starts from zero | `journal_cold_start` (v3) | Hot/warm/cold cache — loads 3 files instead of 28 |
|
|
56
|
+
|
|
57
|
+
**Memory solves forgetting. AgentRecall solves misunderstanding.**
|
|
61
58
|
|
|
62
59
|
---
|
|
63
60
|
|
|
64
61
|
## Quick Start
|
|
65
62
|
|
|
66
|
-
###
|
|
63
|
+
### MCP Server (any agent)
|
|
67
64
|
|
|
68
65
|
```bash
|
|
66
|
+
# Claude Code
|
|
69
67
|
claude mcp add agent-recall -- npx -y agent-recall-mcp
|
|
70
|
-
```
|
|
71
68
|
|
|
72
|
-
|
|
73
|
-
|
|
74
|
-
|
|
75
|
-
|
|
76
|
-
{
|
|
77
|
-
"mcpServers": {
|
|
78
|
-
"agent-recall": {
|
|
79
|
-
"command": "npx",
|
|
80
|
-
"args": ["-y", "agent-recall-mcp"]
|
|
81
|
-
}
|
|
82
|
-
}
|
|
83
|
-
}
|
|
69
|
+
# Cursor — .cursor/mcp.json
|
|
70
|
+
{ "mcpServers": { "agent-recall": { "command": "npx", "args": ["-y", "agent-recall-mcp"] } } }
|
|
71
|
+
|
|
72
|
+
# VS Code — .vscode/mcp.json
|
|
73
|
+
{ "servers": { "agent-recall": { "command": "npx", "args": ["-y", "agent-recall-mcp"] } } }
|
|
84
74
|
```
|
|
85
75
|
|
|
86
|
-
###
|
|
76
|
+
### Skill (Claude Code)
|
|
77
|
+
|
|
78
|
+
```bash
|
|
79
|
+
mkdir -p ~/.claude/skills/agent-recall
|
|
80
|
+
curl -o ~/.claude/skills/agent-recall/SKILL.md \
|
|
81
|
+
https://raw.githubusercontent.com/NovadaLabs/AgentRecall/main/SKILL.md
|
|
82
|
+
```
|
|
87
83
|
|
|
88
|
-
|
|
84
|
+
Say **"save"** to journal. Say **"read the latest journal"** to resume.
|
|
89
85
|
|
|
90
86
|
---
|
|
91
87
|
|
|
92
|
-
## 12 Tools
|
|
88
|
+
## 12 MCP Tools
|
|
93
89
|
|
|
94
90
|
### Session Memory (6 tools)
|
|
95
91
|
|
|
96
|
-
| Tool |
|
|
97
|
-
|
|
98
|
-
| `journal_read` | Read entry by date or
|
|
99
|
-
| `journal_write` |
|
|
100
|
-
| `journal_capture` | Lightweight Q&A capture
|
|
101
|
-
| `journal_list` | List recent entries
|
|
102
|
-
| `journal_search` | Full-text search across
|
|
103
|
-
| `journal_projects` | List all tracked projects
|
|
92
|
+
| Tool | Purpose |
|
|
93
|
+
|------|---------|
|
|
94
|
+
| `journal_read` | Read entry by date or "latest". Filter by section. |
|
|
95
|
+
| `journal_write` | Write or update journal content |
|
|
96
|
+
| `journal_capture` | Lightweight L1 Q&A capture |
|
|
97
|
+
| `journal_list` | List recent entries |
|
|
98
|
+
| `journal_search` | Full-text search across history |
|
|
99
|
+
| `journal_projects` | List all tracked projects |
|
|
104
100
|
|
|
105
|
-
### v3 Architecture (3 tools) — NEW
|
|
101
|
+
### v3 Architecture (3 tools) — NEW
|
|
106
102
|
|
|
107
|
-
| Tool |
|
|
108
|
-
|
|
109
|
-
| `journal_state` | **
|
|
110
|
-
| `journal_cold_start` | **Cache-aware cold start** — HOT (today+yesterday
|
|
111
|
-
| `journal_archive` | **Archive old entries** — moves
|
|
103
|
+
| Tool | Purpose |
|
|
104
|
+
|------|---------|
|
|
105
|
+
| `journal_state` | **JSON state layer** — structured read/write for agent-to-agent handoffs (milliseconds, no prose) |
|
|
106
|
+
| `journal_cold_start` | **Cache-aware cold start** — HOT (today+yesterday), WARM (2-7 days), COLD (7+ days) |
|
|
107
|
+
| `journal_archive` | **Archive old entries** — moves to `archive/` with summaries, keeps journal/ clean |
|
|
112
108
|
|
|
113
109
|
### Alignment & Synthesis (3 tools)
|
|
114
110
|
|
|
115
|
-
| Tool |
|
|
116
|
-
|
|
117
|
-
| `alignment_check` | Record
|
|
118
|
-
| `nudge` | Surface
|
|
119
|
-
| `context_synthesize` |
|
|
111
|
+
| Tool | Purpose |
|
|
112
|
+
|------|---------|
|
|
113
|
+
| `alignment_check` | Record confidence + assumptions + human corrections |
|
|
114
|
+
| `nudge` | Surface contradiction between current and past input |
|
|
115
|
+
| `context_synthesize` | L3 synthesis: patterns, contradictions, goal evolution |
|
|
120
116
|
|
|
121
117
|
---
|
|
122
118
|
|
|
123
|
-
##
|
|
119
|
+
## How Alignment Detection Works
|
|
120
|
+
|
|
121
|
+
When an agent isn't sure it understands:
|
|
124
122
|
|
|
125
123
|
```
|
|
126
|
-
|
|
127
|
-
|
|
128
|
-
|
|
129
|
-
|
|
130
|
-
|
|
131
|
-
│ │ Memory │ │ (daily) │ │ (cross-session) │ │
|
|
132
|
-
│ │ ~50 tokens │ │ ~800 tokens │ │ ~200 tokens │ │
|
|
133
|
-
│ │ │ │ │ │ │ │
|
|
134
|
-
│ │ journal_ │ │ journal_ │ │ context_ │ │
|
|
135
|
-
│ │ capture │ │ write/read │ │ synthesize │ │
|
|
136
|
-
│ └──────┬───────┘ └──────┬───────┘ └────────┬─────────┘ │
|
|
137
|
-
│ │ synthesized │ synthesized │ │
|
|
138
|
-
│ └────────►─────────┘────────►───────────┘ │
|
|
139
|
-
│ │
|
|
140
|
-
│ ┌──────────────────────────────────────────────────────┐ │
|
|
141
|
-
│ │ v3: JSON State Layer (agent-to-agent, no prose) │ │
|
|
142
|
-
│ │ journal_state → .state.json alongside .md │ │
|
|
143
|
-
│ └──────────────────────────────────────────────────────┘ │
|
|
144
|
-
│ │
|
|
145
|
-
│ ┌──────────────────────────────────────────────────────┐ │
|
|
146
|
-
│ │ v3: Cache Layer (hot/warm/cold) │ │
|
|
147
|
-
│ │ journal_cold_start → loads 3 files, not 28 │ │
|
|
148
|
-
│ └──────────────────────────────────────────────────────┘ │
|
|
149
|
-
└─────────────────────────────────────────────────────────────┘
|
|
124
|
+
ALIGNMENT CHECK:
|
|
125
|
+
- Goal: Build a REST API for user management
|
|
126
|
+
- Confidence: medium
|
|
127
|
+
- Assumptions: PostgreSQL, no auth yet, CRUD only
|
|
128
|
+
- Unclear: Should this include role-based access?
|
|
150
129
|
```
|
|
151
130
|
|
|
152
|
-
|
|
131
|
+
Human confirms or corrects. The delta is logged. Over time, patterns reveal where misunderstanding is most likely.
|
|
153
132
|
|
|
154
|
-
##
|
|
133
|
+
## How Nudge Protocol Works
|
|
155
134
|
|
|
156
|
-
|
|
157
|
-
┌─ HOT (0-1 day) ─────────────────────────────────┐
|
|
158
|
-
│ Full JSON state + brief from markdown │
|
|
159
|
-
│ → Everything the next agent needs │
|
|
160
|
-
└──────────────────────────────────────────────────┘
|
|
161
|
-
↓
|
|
162
|
-
┌─ WARM (2-7 days) ────────────────────────────────┐
|
|
163
|
-
│ Brief summary only (first 2KB of journal) │
|
|
164
|
-
│ → "What happened this week" context │
|
|
165
|
-
└──────────────────────────────────────────────────┘
|
|
166
|
-
↓
|
|
167
|
-
┌─ COLD (7+ days) ─────────────────────────────────┐
|
|
168
|
-
│ Count only. Use journal_read for full content. │
|
|
169
|
-
│ Use journal_archive to move to archive/ folder. │
|
|
170
|
-
└──────────────────────────────────────────────────┘
|
|
171
|
-
```
|
|
135
|
+
When the agent detects the human contradicts a prior decision:
|
|
172
136
|
|
|
173
|
-
|
|
174
|
-
|
|
175
|
-
|
|
176
|
-
|
|
177
|
-
|
|
178
|
-
{
|
|
179
|
-
"version": "2.1.1",
|
|
180
|
-
"date": "2026-04-07",
|
|
181
|
-
"project": "my-project",
|
|
182
|
-
"completed": [
|
|
183
|
-
{ "task": "built dashboard", "result": "11 pages, 35 tabs" }
|
|
184
|
-
],
|
|
185
|
-
"failures": [
|
|
186
|
-
{ "task": "extraction", "what_went_wrong": "missed sub-tabs", "root_cause": "context fatigue", "fixed": true }
|
|
187
|
-
],
|
|
188
|
-
"state": {
|
|
189
|
-
"genome": { "status": "v3.2", "details": "8 dimensions" }
|
|
190
|
-
},
|
|
191
|
-
"next_actions": [
|
|
192
|
-
{ "priority": "P0", "task": "verify against real site" }
|
|
193
|
-
],
|
|
194
|
-
"insights": [
|
|
195
|
-
{ "claim": "extraction quality = replication quality", "confidence": "high", "evidence": "4 sites tested" }
|
|
196
|
-
],
|
|
197
|
-
"counts": { "pages": 91, "tabs": 35, "api_routes": 3 }
|
|
198
|
-
}
|
|
137
|
+
```
|
|
138
|
+
NUDGE:
|
|
139
|
+
- You decided Clerk for auth on March 25.
|
|
140
|
+
- Now you're asking for custom auth from scratch.
|
|
141
|
+
- Has the goal changed, or should we stick with Clerk?
|
|
199
142
|
```
|
|
200
143
|
|
|
201
|
-
|
|
144
|
+
Not the agent being difficult — it's helping the human **clarify their own thinking.**
|
|
202
145
|
|
|
203
146
|
---
|
|
204
147
|
|
|
205
|
-
##
|
|
148
|
+
## Three-Layer Memory + v3 Cache
|
|
206
149
|
|
|
207
150
|
```
|
|
208
|
-
|
|
209
|
-
|
|
210
|
-
|
|
211
|
-
|
|
212
|
-
|
|
213
|
-
|
|
214
|
-
|
|
215
|
-
|
|
216
|
-
|
|
217
|
-
|
|
218
|
-
|
|
219
|
-
|
|
151
|
+
┌─────────────────────────────────────────────────────────┐
|
|
152
|
+
│ L1: Working Memory [per-turn, ~50 tok] "What happened"│
|
|
153
|
+
│ ↓ synthesized into │
|
|
154
|
+
│ L2: Episodic Memory [daily, ~800 tok] "What it means"│
|
|
155
|
+
│ ↓ synthesized into │
|
|
156
|
+
│ L3: Semantic Memory [cross-session] "What's true" │
|
|
157
|
+
│ (contradiction detection + goal evolution) │
|
|
158
|
+
├─────────────────────────────────────────────────────────┤
|
|
159
|
+
│ v3: JSON State Layer [per-session] Agent-to-agent data │
|
|
160
|
+
│ journal_state → .state.json alongside .md │
|
|
161
|
+
├─────────────────────────────────────────────────────────┤
|
|
162
|
+
│ v3: Cache Layer HOT (0-1d) → WARM (2-7d) → COLD │
|
|
163
|
+
│ journal_cold_start → loads 3 files, not 28 │
|
|
164
|
+
└─────────────────────────────────────────────────────────┘
|
|
220
165
|
```
|
|
221
166
|
|
|
222
167
|
---
|
|
@@ -227,35 +172,40 @@ Every session follows a structured quality cycle:
|
|
|
227
172
|
|
|
228
173
|
```
|
|
229
174
|
🧠 THINK → Was the approach right? Was research done?
|
|
230
|
-
⚡ EXECUTE → What happened vs
|
|
231
|
-
🔍 REFLECT → 5-dimension quality score + Intelligent Distance gap
|
|
175
|
+
⚡ EXECUTE → What happened vs planned? (COUNTS, not feelings)
|
|
176
|
+
🔍 REFLECT → 5-dimension quality score + Intelligent Distance gap
|
|
232
177
|
🔄 FEEDBACK → Loop (needs iteration) or Exit (quality sufficient)
|
|
233
178
|
```
|
|
234
179
|
|
|
235
|
-
**
|
|
236
|
-
|
|
237
|
-
|
|
238
|
-
|
|
239
|
-
> Not just successes. Failures are more valuable for learning.
|
|
180
|
+
**The Reflect step explicitly measures Intelligent Distance:**
|
|
181
|
+
- What user meant vs what I interpreted
|
|
182
|
+
- The gap between them (or "none — aligned")
|
|
183
|
+
- What to change so the gap shrinks next time
|
|
240
184
|
|
|
241
185
|
---
|
|
242
186
|
|
|
243
|
-
##
|
|
187
|
+
## Supported Agents
|
|
244
188
|
|
|
245
|
-
|
|
|
246
|
-
|
|
247
|
-
|
|
|
248
|
-
|
|
|
189
|
+
| Agent | Skill | MCP | Protocol |
|
|
190
|
+
|-------|:-----:|:---:|:--------:|
|
|
191
|
+
| Claude Code | ✅ | ✅ | ✅ |
|
|
192
|
+
| Cursor | ⚡ | ✅ | ✅ |
|
|
193
|
+
| VS Code Copilot | — | ✅ | ✅ |
|
|
194
|
+
| Windsurf | ⚡ | ✅ | ✅ |
|
|
195
|
+
| Claude Desktop | — | ✅ | ✅ |
|
|
196
|
+
| Any MCP agent | — | ✅ | ✅ |
|
|
197
|
+
| Any AI agent | — | — | ✅ (manual) |
|
|
249
198
|
|
|
250
199
|
---
|
|
251
200
|
|
|
252
|
-
##
|
|
201
|
+
## Real Results
|
|
253
202
|
|
|
254
|
-
|
|
255
|
-
|
|
256
|
-
|
|
257
|
-
|
|
258
|
-
|
|
203
|
+
Validated over **30+ sessions** across 5 production projects:
|
|
204
|
+
- Cold-start: **5 min → 2 seconds** (with v3 cache: loads 3 files not 28)
|
|
205
|
+
- Decision history: **0% → 100% retained** across sessions
|
|
206
|
+
- Misunderstanding caught before wrong work: **6+ instances** via alignment checks
|
|
207
|
+
- Quality loop caught **4 code review gaps** that would have shipped
|
|
208
|
+
- Failures section prevented **3 repeated mistakes** across agent handoffs
|
|
259
209
|
|
|
260
210
|
---
|
|
261
211
|
|
|
@@ -263,92 +213,19 @@ npx agent-recall-mcp --list-tools # List all 12 tools as JSON
|
|
|
263
213
|
|
|
264
214
|
Built by [tongwu](https://github.com/Goldentrii) at [NovadaLabs](https://github.com/NovadaLabs).
|
|
265
215
|
|
|
266
|
-
**We'd love your feedback
|
|
216
|
+
**We'd love your feedback:**
|
|
267
217
|
|
|
268
218
|
- Email: tongwu0824@gmail.com
|
|
269
219
|
- GitHub Issues: [NovadaLabs/AgentRecall](https://github.com/NovadaLabs/AgentRecall/issues)
|
|
270
220
|
|
|
271
|
-
|
|
272
|
-
|
|
273
|
-
|
|
274
|
-
|
|
275
|
-
MIT
|
|
276
|
-
|
|
277
|
-
---
|
|
221
|
+
1. **Use the protocol** for a week → [report](https://github.com/NovadaLabs/AgentRecall/issues)
|
|
222
|
+
2. **Implement it** in a new agent → PR welcome
|
|
223
|
+
3. **Improve the spec** → [protocol doc](docs/intelligent-distance-protocol.md)
|
|
278
224
|
|
|
279
225
|
---
|
|
280
226
|
|
|
281
|
-
|
|
282
|
-
|
|
283
|
-
> 给你的 AI 智能体一个跨会话记忆的大脑。
|
|
284
|
-
|
|
285
|
-
MCP 服务器 — 双层会话记忆 + v3 JSON 状态层 + 缓存感知冷启动 + Think-Execute-Reflect 质量循环。兼容所有 MCP 客户端。
|
|
286
|
-
|
|
287
|
-
**零云端。零遥测。所有数据保存在本地。**
|
|
288
|
-
|
|
289
|
-
---
|
|
290
|
-
|
|
291
|
-
## 快速开始
|
|
292
|
-
|
|
293
|
-
```bash
|
|
294
|
-
# Claude Code
|
|
295
|
-
claude mcp add agent-recall -- npx -y agent-recall-mcp
|
|
296
|
-
|
|
297
|
-
# Cursor: .cursor/mcp.json
|
|
298
|
-
{ "mcpServers": { "agent-recall": { "command": "npx", "args": ["-y", "agent-recall-mcp"] } } }
|
|
299
|
-
```
|
|
300
|
-
|
|
301
|
-
---
|
|
302
|
-
|
|
303
|
-
## 12 个工具
|
|
304
|
-
|
|
305
|
-
### 会话记忆（6 个）
|
|
306
|
-
|
|
307
|
-
| 工具 | 功能 |
|
|
308
|
-
|------|------|
|
|
309
|
-
| `journal_read` | 按日期读取日志，支持章节过滤 |
|
|
310
|
-
| `journal_write` | 追加或替换今日日志 |
|
|
311
|
-
| `journal_capture` | 轻量问答捕获 |
|
|
312
|
-
| `journal_list` | 列出最近日志 |
|
|
313
|
-
| `journal_search` | 全文搜索 |
|
|
314
|
-
| `journal_projects` | 列出所有项目 |
|
|
315
|
-
|
|
316
|
-
### v3 架构（3 个）— v2.1.1 新增
|
|
317
|
-
|
|
318
|
-
| 工具 | 功能 |
|
|
319
|
-
|------|------|
|
|
320
|
-
| `journal_state` | **JSON 状态层** — 结构化读写，agent 间毫秒级交接 |
|
|
321
|
-
| `journal_cold_start` | **缓存感知冷启动** — 热/温/冷三级，加载 3 个文件而非 28 个 |
|
|
322
|
-
| `journal_archive` | **归档旧条目** — 移至 archive/，保留单行摘要 |
|
|
323
|
-
|
|
324
|
-
### 对齐 & 合成（3 个）
|
|
325
|
-
|
|
326
|
-
| 工具 | 功能 |
|
|
327
|
-
|------|------|
|
|
328
|
-
| `alignment_check` | 记录理解度、置信度、人类纠正 |
|
|
329
|
-
| `nudge` | 检测矛盾，主动提问 |
|
|
330
|
-
| `context_synthesize` | 跨会话合成：目标演变、决策历史、模式检测 |
|
|
331
|
-
|
|
332
|
-
---
|
|
333
|
-
|
|
334
|
-
## 核心理念：智能距离（Intelligent Distance）
|
|
335
|
-
|
|
336
|
-
> *「人类智能与 AI 智能之间的差距是结构性的、永久的 — 不是一个临时的技术问题。」*
|
|
337
|
-
|
|
338
|
-
人类是「生出来的」（具身经验）、机器是「造出来的」（规则驱动）、AI 是「训练出来的」（统计共现）。三种不同的认知基底，产生三种不同的理解方式。这个差距就是**智能距离**。
|
|
339
|
-
|
|
340
|
-
AgentRecall 不试图缩小这个差距，而是构建一个**协议**来最小化信息损失：
|
|
341
|
-
- `alignment_check` — 在开始工作前记录理解和假设，让人类纠正
|
|
342
|
-
- `nudge` — 检测到矛盾时主动提问，而不是默默构建错误的东西
|
|
343
|
-
- Think-Execute-Reflect — 用数字而非感觉评估质量（「建了 11 页 35 个标签」而非「做得不错」）
|
|
344
|
-
- `journal_state` (JSON) — agent 间用结构化数据交接，不靠散文解析
|
|
345
|
-
|
|
346
|
-
**记忆解决遗忘，AgentRecall 解决误解。**
|
|
347
|
-
|
|
348
|
-
---
|
|
349
|
-
|
|
350
|
-
## 许可证
|
|
227
|
+
## License
|
|
351
228
|
|
|
352
|
-
MIT — [tongwu](https://github.com/Goldentrii)
|
|
229
|
+
MIT — *Concept & Design: [tongwu](https://github.com/Goldentrii)*
|
|
353
230
|
|
|
354
|
-
|
|
231
|
+
**Memory solves forgetting. AgentRecall solves misunderstanding.**
|
package/dist/index.js
CHANGED
|
@@ -11,7 +11,7 @@ const execFileAsync = promisify(execFile);
|
|
|
11
11
|
// ---------------------------------------------------------------------------
|
|
12
12
|
// Constants
|
|
13
13
|
// ---------------------------------------------------------------------------
|
|
14
|
-
const VERSION = "3.2.
|
|
14
|
+
const VERSION = "3.2.2";
|
|
15
15
|
const JOURNAL_ROOT = process.env.AGENT_RECALL_ROOT ||
|
|
16
16
|
path.join(os.homedir(), ".agent-recall");
|
|
17
17
|
const LEGACY_ROOT = path.join(os.homedir(), ".claude", "projects");
|
package/package.json
CHANGED