mnemos-capture 1.0.2 → 1.0.3
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 +0 -11
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -55,17 +55,6 @@ Mnemos handles any text-based input. Paste it, and the LLM figures out the forma
|
|
|
55
55
|
|
|
56
56
|
Coming soon: voice memos, URL auto-fetch, and browser extension for one-click capture.
|
|
57
57
|
|
|
58
|
-
## What the LLM extracts
|
|
59
|
-
|
|
60
|
-
Every capture produces a structured Markdown file with:
|
|
61
|
-
|
|
62
|
-
- **Core idea** — the actual insight, not "this article discusses X"
|
|
63
|
-
- **Key takeaways** — 3-5 specific, opinionated assertions that pass the "so what?" test
|
|
64
|
-
- **Quotes** — only verbatim lines worth keeping. None if nothing is genuinely quotable
|
|
65
|
-
- **Tags** — 2-5 topic tags relevant to the content (e.g. `product-discovery`, `ai-agents`, `pricing`)
|
|
66
|
-
- **Applied to** — one sentence connecting this to something you're building right now
|
|
67
|
-
- **Low confidence flag** — alerts you when input is too short or ambiguous for reliable extraction
|
|
68
|
-
|
|
69
58
|
## Cost
|
|
70
59
|
|
|
71
60
|
Mnemos uses your own Anthropic API key (BYOK — you bring your own key, Mnemos never charges you).
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "mnemos-capture",
|
|
3
|
-
"version": "1.0.
|
|
3
|
+
"version": "1.0.3",
|
|
4
4
|
"description": "Zero-friction knowledge capture for agentic workflows. Paste anything → Claude extracts insights → auto-commits to your knowledge repo → your Claude Code workflow picks it up.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"bin": {
|