@velvetmonkey/flywheel-memory 2.1.4 → 2.3.0

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.
Files changed (4) hide show
  1. package/LICENSE +201 -661
  2. package/README.md +14 -396
  3. package/dist/index.js +3063 -828
  4. package/package.json +3 -2
package/README.md CHANGED
@@ -1,402 +1,20 @@
1
- <div align="center">
2
- <img src="https://raw.githubusercontent.com/velvetmonkey/flywheel-memory/main/header.png" alt="Flywheel" width="256"/>
3
- <h1>Flywheel</h1>
4
- <p><strong>MCP tools that search, write, and auto-link your Obsidian vault — and learn from your edits.</strong><br/>All local. All yours. A few lines of config.</p>
5
- </div>
1
+ # Flywheel
6
2
 
7
- **Search** — One call returns section provenance, extracted dates, entity bridges, and confidence scores. Your AI decides what to read next without opening any files.
3
+ > **See the [main README](../../README.md) for documentation, demos, and benchmarks.**
8
4
 
9
- **Write** — Every mutation auto-links entities across your vault. Names, projects, and relationships wikilinked in real time.
5
+ ## Quick links
10
6
 
11
- **Remember** — Links you keep get stronger. Links you remove get suppressed. The graph compounds with use.
12
-
13
- [![npm version](https://img.shields.io/npm/v/@velvetmonkey/flywheel-memory.svg)](https://www.npmjs.com/package/@velvetmonkey/flywheel-memory)
14
- [![MCP](https://img.shields.io/badge/MCP-Model%20Context%20Protocol-blueviolet.svg)](https://modelcontextprotocol.io/)
15
- [![CI](https://github.com/velvetmonkey/flywheel-memory/actions/workflows/ci.yml/badge.svg)](https://github.com/velvetmonkey/flywheel-memory/actions/workflows/ci.yml)
16
- [![License: Apache-2.0](https://img.shields.io/badge/License-Apache--2.0-blue.svg)](https://www.apache.org/licenses/LICENSE-2.0)
17
- [![Platform](https://img.shields.io/badge/platform-macOS%20%7C%20Linux%20%7C%20Windows-blue.svg)](https://github.com/velvetmonkey/flywheel-memory)
18
- [![Scale](https://img.shields.io/badge/scale-100k--line%20files%20%7C%202.5k%20entities-brightgreen.svg)](https://github.com/velvetmonkey/flywheel-memory/blob/main/docs/TESTING.md#performance-benchmarks)
19
- [![Tests](https://img.shields.io/badge/tests-2,482%20passed-brightgreen.svg)](https://github.com/velvetmonkey/flywheel-memory/blob/main/docs/TESTING.md)
20
-
21
- | | Grep approach | Flywheel |
22
- |---|---|---|
23
- | "What's overdue?" | Grep + read matches (~500-2,000 tokens) | Indexed metadata query (~50-200 tokens) |
24
- | "What links here?" | Grep for note name (flat list, no graph) | Pre-indexed backlink graph (<10ms) |
25
- | "Add a meeting note" | Raw write, no linking | Structured write + auto-wikilink |
26
- | "What should I link?" | Not possible | 10-dimension scoring + semantic search |
27
- | Hubs, orphans, paths? | Not possible | Pre-indexed graph analysis |
28
-
29
- 75 tools across 12 categories. 6-line config. Zero cloud dependencies.
30
-
31
- **Try in 60 seconds:**
32
-
33
- ```bash
34
- git clone https://github.com/velvetmonkey/flywheel-memory.git
35
- cd flywheel-memory/demos/carter-strategy && claude
36
- ```
37
-
38
- Then ask: *"How much have I billed Acme Corp?"*
39
-
40
- ---
41
-
42
- ## See It Work
43
-
44
- ### Read: "How much have I billed Acme Corp?"
45
-
46
- From the [carter-strategy](https://github.com/velvetmonkey/flywheel-memory/tree/main/demos/carter-strategy/) demo -- a solo consultant with 3 clients, 5 projects, and $27K in invoices.
47
-
48
- ```
49
- ❯ How much have I billed Acme Corp?
50
-
51
- ● flywheel › search
52
- query: "Acme Corp"
53
- → clients/Acme Corp.md, invoices/INV-2025-047.md,
54
- invoices/INV-2025-048.md, projects/Acme Data Migration.md
55
-
56
- ● read_file("clients/Acme Corp.md")
57
- ← total_billed: 156000, rate: $300/hr, status: active
58
-
59
- ● read_file("invoices/INV-2025-047.md")
60
- ← amount: 15000, status: paid, period: November 2025
61
-
62
- ● read_file("invoices/INV-2025-048.md")
63
- ← amount: 12000, status: pending, period: December 2025
64
-
65
- ┌─ RESULT ──────────────────────────────────────────────┐
66
- │ Acme Corp: $156K total billed │
67
- │ │
68
- │ Paid: $15,000 — Acme Data Migration (Nov 2025) │
69
- │ Pending: $12,000 — Acme Data Migration (Dec 2025) │
70
- │ │
71
- │ Also: $35K pending proposal (Analytics Add-on) │
72
- └───────────────────────────────────────────────────────┘
73
- ```
74
-
75
- [[Flywheel]]'s indexed search found all Acme-related notes in one call. The AI read the files it needed for billing details. No grepping, no guessing paths.
76
-
77
- Flywheel's search found all related notes in one call. Without it, the AI would grep for "Acme" and scan every matching file.
78
-
79
- The bigger difference isn't just tokens — it's that Flywheel answers structural questions (backlinks, hubs, shortest paths, schema analysis) that file-level access can't answer at all.
80
-
81
- ### Write: Auto-wikilinks on every mutation
82
-
83
- ```
84
- ❯ Log that Stacy Thompson reviewed the API Security Checklist for Acme before the Beta Corp Dashboard kickoff
85
-
86
- ● flywheel › vault_add_to_section
87
- path: "daily-notes/2026-01-04.md"
88
- section: "Log"
89
- content: "[[Stacy Thompson]] reviewed the [[API Security Checklist]] for [[Acme Corp|Acme]] before the [[Beta Corp Dashboard]] kickoff → [[GlobalBank API Audit]], [[Acme Analytics Add-on]], [[Acme Data Migration]]"
90
- ↑ 4 entities auto-linked — "Acme" resolved to Acme Corp via alias
91
- → 3 contextual suggestions appended (scored ≥12 via co-occurrence with linked entities)
92
- ```
93
-
94
- Try it yourself: `cd demos/carter-strategy && claude`
95
-
96
- ---
97
-
98
- ## What Makes Flywheel Different
99
-
100
- ### 1. Hybrid Search
101
-
102
- Search "authentication" -- exact matches. Search "login security" -- same notes, plus every note about auth that never uses the word.
103
-
104
- Keyword search finds what you said. Semantic search finds what you meant. Flywheel runs both, fuses the results via Reciprocal Rank Fusion, and U-shaped interleaves them so the best results land at attention peaks. Top results include the full section content around each match -- a decision surface, not a list of filenames. Runs locally on a 23 MB model with contextual embedding prefixes. Nothing leaves your machine.
105
-
106
- ### 2. Every Suggestion Has a Receipt
107
-
108
- Ask why Flywheel suggested `[[Marcus Johnson]]`:
109
-
110
- ```
111
- Entity Score Match Co-oc Type Context Recency Cross Hub Feedback Semantic Edge
112
- ──────────────────────────────────────────────────────────────────────────────────────────────────────
113
- Marcus Johnson 34 +10 +3 +5 +5 +5 +3 +1 +2 0 0
114
- ```
115
-
116
- 10 scoring dimensions, every number traceable to vault usage. Recency came from what you last wrote. Co-occurrence came from notes you've written before. Hub came from how many other notes link there. The score learns as you use it.
117
-
118
- See [docs/ALGORITHM.md](https://github.com/velvetmonkey/flywheel-memory/blob/main/docs/ALGORITHM.md) for how scoring works.
119
-
120
- ### 3. The Self-Improving Loop
121
-
122
- **Every interaction is a graph-building operation — and a learning signal.**
123
-
124
- When you write a note, entities are auto-linked — creating edges. When you keep a `[[link]]` through 10 edits, that edge gains weight. When two entities appear together in 20 notes, they build a co-occurrence bond (NPMI — a measure of how strongly two things associate beyond chance). When you read frequently, recent entities surface in suggestions. When you remove a bad link, the system learns what to stop suggesting (it tracks accept/reject ratios per entity and gradually suppresses low-quality matches).
125
-
126
- This is the uncontested gap — no competitor has a feedback loop that learns from knowledge management actions.
127
-
128
- We prove it: auto-linked entities achieve 100% entity precision (never suggests a non-existent entity), 51% strict precision, and the system finds 72–82% of links it should (recall) — stable over 50 generations of noisy feedback. See [Graph Quality](#graph-quality) below.
129
-
130
- Result: a queryable graph. "What's the shortest path between AlphaFold and my docking experiment?" Backlinks, forward links, hubs, orphans, shortest paths — every query leverages hundreds of accumulated connections. Denser graphs make every query more precise.
131
-
132
- ### 4. Semantic Understanding
133
-
134
- Content about "deployment automation" suggests `[[CI/CD]]` — no keyword match needed. Entity-level embeddings mean your knowledge graph understands meaning, not just words.
135
-
136
- - **Semantic bridges**: Discovers high-value missing links between conceptually related but unlinked notes
137
- - **Semantic clusters**: Groups notes by meaning instead of folder structure
138
- - **Semantic wikilinks**: Suggestions based on what you *mean*, not just what you typed
139
-
140
- Build once with `init_semantic`. Each note is embedded with a contextual prefix (title + tags) so the vector carries document identity alongside content meaning. Everything upgrades automatically. Configurable model via `EMBEDDING_MODEL` env var.
141
-
142
- ### 5. Agentic Memory
143
-
144
- The system remembers context across sessions. No more starting from scratch.
145
-
146
- - **`brief`** assembles startup context: recent sessions, active entities, stored memories, corrections, vault pulse — token-budgeted
147
- - **`search`** retrieves across all knowledge channels: notes, entities, and memories in one call — returns a decision surface with section content, bridges, and confidence scores
148
- - **`memory`** stores observations with confidence decay, TTL, and lifecycle management
149
-
150
- Your AI picks up where it left off.
151
-
152
- ### How It Compares to Other Approaches
153
-
154
- | | Pure Vector Search | Pure Keyword Search | Flywheel |
155
- |---|---|---|---|
156
- | "Why was this suggested?" | "Embeddings are close" | "Term frequency" | "10 + 3 + 5 + 5 + 3 + 1 = 34" |
157
- | Semantic wikilinks | No | No | Yes (semantic) |
158
- | Finds synonyms/concepts? | Yes | No | Yes (semantic search) |
159
- | Exact phrase matching? | Weak | Yes | Yes |
160
- | Same input → same output? | Not guaranteed | Always | Always |
161
- | Runs offline? | Often not | Yes | Yes (local embeddings) |
162
- | Learns from usage? | Retraining | No | Implicit feedback loop |
163
- | Agent memory | No | No | Yes (brief + search + memory) |
164
-
165
- ---
166
-
167
- ## The Flywheel Effect
168
-
169
- The name is literal. A flywheel is hard to start but once spinning, each push adds to the momentum.
170
-
171
- ### Day 1: Instant Value
172
-
173
- You point Flywheel at your vault. It indexes every note, extracts entities, builds a backlink graph. First query returns in <10ms. First write auto-links three entities you would have missed. No training period. No configuration.
174
-
175
- ### Week 1: Connections Appear
176
-
177
- You have 30 disconnected notes. Auto-wikilinks create 47 connections on your first day of writing through Flywheel. You stop reading files and start querying a graph.
178
-
179
- ### Month 1: Intelligence Emerges
180
-
181
- Hub notes surface. "[[Sarah Mitchell]]" has 23 backlinks -- she's clearly important. When you write about a project, her name appears in suggestions because co-occurrence tracking knows she's relevant. You didn't configure this. The vault structure revealed it.
182
-
183
- ### Month 3: The Graph Is Self-Sustaining
184
-
185
- Every query leverages hundreds of accumulated connections. New content auto-links to the right places. You stop thinking about organization.
186
-
187
- ### What This Looks Like
188
-
189
- ```mermaid
190
- graph LR
191
- W[Write] --> A[Auto-link]
192
- A --> D[Denser Graph]
193
- D --> B[Better Queries]
194
- B --> M[More Use]
195
- M --> W
196
- ```
197
-
198
- ```
199
- Input: "Stacy Thompson finished reviewing the API Security Checklist for the Beta Corp Dashboard"
200
- Output: "[[Stacy Thompson]] finished reviewing the [[API Security Checklist]] for the [[Beta Corp Dashboard]]"
201
- ```
202
-
203
- No manual linking. No broken references. Use compounds into structure, structure compounds into intelligence.
204
-
205
- ---
206
-
207
- ## Battle-Tested
208
-
209
- **2,482 tests. 122 test files. 47,000+ lines of test code.**
210
-
211
- ### Performance
212
-
213
- | Operation | Threshold | Typical |
214
- |---|---|---|
215
- | 1k-line mutation | <100ms | ~15ms |
216
- | 10k-line mutation | <500ms | -- |
217
- | 100k-line mutation | <2s | -- |
218
-
219
- - **100 parallel writes, zero corruption** -- concurrent mutations verified under stress
220
- - **Property-based fuzzing** -- fast-check with 700+ randomized scenarios
221
- - **SQL injection prevention** -- parameterized queries throughout
222
- - **Path traversal blocking** -- all file paths validated against vault root
223
- - **Deterministic output** -- every tool produces the same result given the same input
224
-
225
- Every demo vault is a real test fixture. If it works in the README, it passes in CI.
226
-
227
- ```bash
228
- git clone https://github.com/velvetmonkey/flywheel-memory.git
229
- cd flywheel-memory && npm install && npm test
230
- ```
231
-
232
- See [docs/PROVE-IT.md](https://github.com/velvetmonkey/flywheel-memory/blob/main/docs/PROVE-IT.md) and [docs/TESTING.md](https://github.com/velvetmonkey/flywheel-memory/blob/main/docs/TESTING.md).
233
-
234
- ### Graph Quality
235
-
236
- The feedback loop claim isn't asserted — it's measured. We build a test vault with known-correct links, strip them out, and measure how well the engine rediscovers them. CI locks these baselines and fails if quality regresses.
237
-
238
- | Mode | Strict Precision | Entity Precision | Recall | F1 |
239
- |---|---|---|---|---|
240
- | Conservative | 51.2% | 100% | 71.7% | 59.7% |
241
- | Balanced | 27.5% | 100% | 76.7% | 40.5% |
242
- | Aggressive | 26.1% | 100% | 76.7% | 39.0% |
243
-
244
- **Precision** = "of the links suggested, how many were correct?" (strict: counts all wrong suggestions; entity precision: excludes known-entity suggestions). **Recall** = "of the links that should exist, how many were found?" **F1** = the balance of both — higher is better.
245
-
246
- Measured against a 96-note/61-entity ground truth vault.
247
-
248
- - **50-generation stress test** — suggest → accept/reject (85% correct, 15% noise) → mutate vault → rebuild index → repeat. F1 holds steady — the feedback loop doesn't degrade under realistic noise.
249
- - **7 vault archetypes** — hub-and-spoke, hierarchical, dense-mesh, sparse-orphan, bridge-network, small-world, chaos
250
- - **13 pipeline stages** (10 scoring dimensions + filters + suppression) individually ablated, contribution measured
251
- - **Regression gate** — CI fails if any mode's F1/precision/recall drops >5pp from baseline
252
-
253
- See [docs/TESTING.md](https://github.com/velvetmonkey/flywheel-memory/blob/main/docs/TESTING.md) for full methodology. Auto-generated report: [docs/QUALITY_REPORT.md](https://github.com/velvetmonkey/flywheel-memory/blob/main/docs/QUALITY_REPORT.md).
254
-
255
- ### Safe Writes
256
-
257
- Every mutation is:
258
-
259
- - **Git-committed** — one `vault_undo_last_mutation` away from reverting any change
260
- - **Conflict-detected** — content hash check prevents clobbering concurrent edits (SHA-256)
261
- - **Policy-governed** — configurable guardrails with warn/strict/off modes
262
- - **Precise** — auto-wikilinks have 1.0 precision in production (never inserts a wrong link)
263
-
264
- ---
265
-
266
- ## How It Compares
267
-
268
- | Feature | Flywheel Memory | Obsidian CLI (MCP) | Smart Connections | Khoj |
269
- |---------|----------------|-------------------|-------------------|------|
270
- | Backlink graph | Bidirectional | No | No | No |
271
- | Hybrid search | Local (keyword + semantic) | No | Cloud only | Cloud |
272
- | Auto-wikilinks | Yes (alias resolution) | No | No | No |
273
- | Schema intelligence | 6 analysis modes | No | No | No |
274
- | Entity extraction | Auto (18 categories) | No | No | No |
275
- | Learns from usage | Feedback loop + suppression | No | No | No |
276
- | Agent memory | brief + search + memory | No | No | No |
277
- | Safe writes | Git + conflict detection | No | N/A | N/A |
278
- | Test coverage | 2,456 tests | Unknown | Unknown | Unknown |
279
- | Tool count | 75 | ~10 | 0 (plugin) | ~5 |
280
-
281
- ---
282
-
283
- ## Try It
284
-
285
- ### Step 1: Try a demo
286
-
287
- ```bash
288
- git clone https://github.com/velvetmonkey/flywheel-memory.git
289
- cd flywheel-memory/demos/carter-strategy && claude
290
- ```
291
-
292
- | Demo | You are | Ask this |
293
- |------|---------|----------|
294
- | [carter-strategy](https://github.com/velvetmonkey/flywheel-memory/tree/main/demos/carter-strategy/) | Solo consultant | "How much have I billed Acme Corp?" |
295
- | [artemis-rocket](https://github.com/velvetmonkey/flywheel-memory/tree/main/demos/artemis-rocket/) | Rocket engineer | "What's blocking propulsion?" |
296
- | [startup-ops](https://github.com/velvetmonkey/flywheel-memory/tree/main/demos/startup-ops/) | SaaS co-founder | "What's our MRR?" |
297
- | [nexus-lab](https://github.com/velvetmonkey/flywheel-memory/tree/main/demos/nexus-lab/) | PhD researcher | "How does AlphaFold connect to my experiment?" |
298
- | [solo-operator](https://github.com/velvetmonkey/flywheel-memory/tree/main/demos/solo-operator/) | Content creator | "How's revenue this month?" |
299
- | [support-desk](https://github.com/velvetmonkey/flywheel-memory/tree/main/demos/support-desk/) | Support agent | "What's Sarah Chen's situation?" |
300
- | [zettelkasten](https://github.com/velvetmonkey/flywheel-memory/tree/main/demos/zettelkasten/) | Zettelkasten student | "How does spaced repetition connect to active recall?" |
301
-
302
- ### Step 2: Your own vault
303
-
304
- Add `.mcp.json` to your vault root:
305
-
306
- ```json
307
- {
308
- "mcpServers": {
309
- "flywheel": {
310
- "command": "npx",
311
- "args": ["-y", "@velvetmonkey/flywheel-memory"],
312
- "env": {
313
- "FLYWHEEL_PRESET": "default"
314
- }
315
- }
316
- }
317
- }
318
- ```
319
-
320
- ```bash
321
- cd /path/to/your/vault && claude
322
- ```
323
-
324
- Defaults to the `default` preset (18 tools). Add bundles as needed. See [docs/CONFIGURATION.md](https://github.com/velvetmonkey/flywheel-memory/blob/main/docs/CONFIGURATION.md) for all options.
325
-
326
- > **Works with any MCP client.** Primarily tested with [[CLAUDE]]. See [Transport Options](#transport-options) for HTTP setup (Cursor, Windsurf, Aider, LangGraph, Ollama, etc.).
327
-
328
- ### Transport Options
329
-
330
- By default, Flywheel uses stdio transport (works with [[Claude Code]] and Claude Desktop). Set `FLYWHEEL_TRANSPORT` to enable HTTP transport for other clients (Cursor, Windsurf, Aider, LangGraph, Ollama):
331
-
332
- | Env Var | Values | Default |
333
- |---------|--------|---------|
334
- | `FLYWHEEL_TRANSPORT` | `stdio`, `http`, `both` | `stdio` |
335
- | `FLYWHEEL_HTTP_PORT` | Port number | `3111` |
336
- | `FLYWHEEL_HTTP_HOST` | Bind address | `127.0.0.1` |
337
-
338
- ```bash
339
- # HTTP only
340
- FLYWHEEL_TRANSPORT=http npx @velvetmonkey/flywheel-memory
341
-
342
- # Both stdio and HTTP simultaneously
343
- FLYWHEEL_TRANSPORT=both npx @velvetmonkey/flywheel-memory
344
-
345
- # Health check
346
- curl http://localhost:3111/health
347
-
348
- # MCP request (JSON-RPC over HTTP)
349
- curl -X POST http://localhost:3111/mcp \
350
- -H "Content-Type: application/json" \
351
- -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
352
- ```
353
-
354
- DNS rebinding protection is automatically enabled when bound to localhost.
355
-
356
- ### Multi-Vault
357
-
358
- Serve multiple Obsidian vaults from a single server:
359
-
360
- ```bash
361
- FLYWHEEL_VAULTS="personal:/path/to/personal,work:/path/to/work" \
362
- FLYWHEEL_TRANSPORT=http npx @velvetmonkey/flywheel-memory
363
- ```
364
-
365
- When multi-vault is active, every tool gains an optional `vault` parameter. The `search` tool automatically searches all vaults when `vault` is omitted, merging results across vaults. Other tools default to the primary vault (first in list).
366
-
367
- ---
368
-
369
- ## Tools Overview
370
-
371
- | Preset | Tools | What you get |
372
- |--------|-------|--------------|
373
- | `default` | 19 | Note-taking essentials — search, read, write, tasks |
374
- | `agent` | 19 | Autonomous AI agents — search, read, write, memory |
375
- | `full` | 69 | Everything — all 12 categories |
376
-
377
- Composable bundles add capabilities to any preset. See [docs/CONFIGURATION.md](https://github.com/velvetmonkey/flywheel-memory/blob/main/docs/CONFIGURATION.md) for all bundles and fine-grained categories.
378
-
379
- The fewer tools you load, the less context the AI needs to pick the right one. See [docs/TOOLS.md](https://github.com/velvetmonkey/flywheel-memory/blob/main/docs/TOOLS.md) for the full reference.
380
-
381
- ---
382
-
383
- ## Documentation
384
-
385
- | Doc | Why read this |
386
- |---|---|
387
- | [PROVE-IT.md](https://github.com/velvetmonkey/flywheel-memory/blob/main/docs/PROVE-IT.md) | See it working in 5 minutes |
388
- | [TOOLS.md](https://github.com/velvetmonkey/flywheel-memory/blob/main/docs/TOOLS.md) | All 75 tools documented |
389
- | [ALGORITHM.md](https://github.com/velvetmonkey/flywheel-memory/blob/main/docs/ALGORITHM.md) | How the scoring works |
390
- | [COOKBOOK.md](https://github.com/velvetmonkey/flywheel-memory/blob/main/docs/COOKBOOK.md) | Example prompts by use case |
391
- | [SETUP.md](https://github.com/velvetmonkey/flywheel-memory/blob/main/docs/SETUP.md) | Full setup guide for your vault |
392
- | [CONFIGURATION.md](https://github.com/velvetmonkey/flywheel-memory/blob/main/docs/CONFIGURATION.md) | Env vars, presets, custom tool sets |
393
- | [ARCHITECTURE.md](https://github.com/velvetmonkey/flywheel-memory/blob/main/docs/ARCHITECTURE.md) | Index strategy, graph, auto-wikilinks |
394
- | [TESTING.md](https://github.com/velvetmonkey/flywheel-memory/blob/main/docs/TESTING.md) | Test methodology and benchmarks |
395
- | [TROUBLESHOOTING.md](https://github.com/velvetmonkey/flywheel-memory/blob/main/docs/TROUBLESHOOTING.md) | Error recovery and diagnostics |
396
- | [VISION.md](https://github.com/velvetmonkey/flywheel-memory/blob/main/docs/VISION.md) | Where this is going |
397
-
398
- ---
7
+ | Doc | What |
8
+ |-----|------|
9
+ | [README](../../README.md) | Overview, demos, get started |
10
+ | [TOOLS.md](../../docs/TOOLS.md) | All tools |
11
+ | [ALGORITHM.md](../../docs/ALGORITHM.md) | Link scoring |
12
+ | [CONFIGURATION.md](../../docs/CONFIGURATION.md) | Env vars, presets |
13
+ | [SETUP.md](../../docs/SETUP.md) | Client setup |
14
+ | [TESTING.md](../../docs/TESTING.md) | Benchmarks, methodology |
15
+ | [ARCHITECTURE.md](../../docs/ARCHITECTURE.md) | Design |
16
+ | [COOKBOOK.md](../../docs/COOKBOOK.md) | Example prompts |
399
17
 
400
18
  ## License
401
19
 
402
- Apache-2.0 — see [LICENSE](https://github.com/velvetmonkey/flywheel-memory/blob/main/LICENSE) for details.
20
+ Apache-2.0