@lincoln504/pi-research 1.6.14 → 1.6.15
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 +17 -22
- package/agent-skill/pi-research/SKILL.md +1 -1
- package/docs/CHANGELOG.md +8 -0
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -32,9 +32,9 @@
|
|
|
32
32
|
<a href="LICENSE"><img alt="License: MIT" src="https://img.shields.io/badge/license-MIT-97ca00?style=flat-square" /></a><br />
|
|
33
33
|
<a href="https://github.com/Lincoln504/pi-research"><img alt="GitHub repository" src="https://img.shields.io/badge/GitHub-Lincoln504%2Fpi--research-181717?style=flat-square&logo=github&logoColor=white" /></a>
|
|
34
34
|
|
|
35
|
-
Search and scraping run locally
|
|
35
|
+
Search and scraping run locally in a stealth browser, with no search provider and no monthly cap. The only cost is LLM tokens.
|
|
36
36
|
|
|
37
|
-
**Current recommended model:** [`inclusionai/ling-3.0-flash`](https://openrouter.ai/inclusionai/ling-3.0-flash) on OpenRouter
|
|
37
|
+
**Current recommended model:** [`inclusionai/ling-3.0-flash`](https://openrouter.ai/inclusionai/ling-3.0-flash) on OpenRouter.
|
|
38
38
|
|
|
39
39
|
### Install
|
|
40
40
|
|
|
@@ -51,40 +51,35 @@ npm install -g @lincoln504/pi-research
|
|
|
51
51
|
pi-research skill install
|
|
52
52
|
```
|
|
53
53
|
|
|
54
|
-
No extra setup is needed. The package
|
|
55
|
-
ready-made bindings for every platform, and the stealth browser (~500MB)
|
|
56
|
-
downloads on first use, so the first scrape takes a few minutes. npm ≥11.19
|
|
57
|
-
skips install scripts by default; leave it that way, nothing needs approving
|
|
58
|
-
or building. Only Windows with npm older than 11.19 can fail when the install
|
|
59
|
-
tries to compile from source; upgrading npm fixes it.
|
|
54
|
+
No extra setup is needed. The package ships ready-made bindings for every platform and runs no install scripts. The stealth browser (~500MB) downloads on first use, so the first scrape takes a few minutes. npm ≥11.19 skips install scripts by default. Leave it that way: nothing needs approving or building. Only Windows with npm older than 11.19 can fail when the install tries to compile from source. Upgrading npm fixes it.
|
|
60
55
|
|
|
61
|
-
In pi
|
|
56
|
+
In pi, the extension works out of the box on the session's model and pi's configuration. Standalone use ([agent skill](docs/AGENT-SKILL.md) or [SDK](docs/SDK.md)) needs a model configured. See [Configuration](docs/CONFIGURATION.md).
|
|
62
57
|
|
|
63
58
|
### Uninstall
|
|
64
59
|
|
|
65
|
-
`pi remove npm:@lincoln504/pi-research` removes the extension
|
|
60
|
+
`pi remove npm:@lincoln504/pi-research` removes the extension. `npm uninstall -g @lincoln504/pi-research` removes the standalone engine. npm 7+ no longer runs `preuninstall`, so nothing else is removed on its own: skill links into other agents (Claude Code, Codex, …), the state directory (`~/.pi/research/state`), and the cache (`~/.cache/pi-research`, including any downloaded embedding models) stay in place. Remove the skill links first with `pi-research skill uninstall` (or `/research-config` → Remove from External Agents). The shared stealth-browser cache (`~/.cache/camoufox`) is preserved unless `PI_RESEARCH_PURGE_BROWSERS=1`. See [AGENT-SKILL.md](docs/AGENT-SKILL.md#installation-flow) for the full picture.
|
|
66
61
|
|
|
67
62
|
### How it works
|
|
68
63
|
|
|
69
|
-
A research run
|
|
64
|
+
A research run works in rounds. A coordinator plans each round and starts the first search, researcher agents scrape and read pages in parallel, and a research lead then either starts another round or writes the final report from everything collected. The result is one cited Markdown report, optionally saved to the knowledge store.
|
|
70
65
|
|
|
71
|
-
Three depth levels (normal, deep, ultra) set the team size and number of rounds.
|
|
66
|
+
Three depth levels (normal, deep, ultra) set the team size and number of rounds. Just describe what you need in plain language, and the tool picks the right one:
|
|
72
67
|
|
|
73
68
|
|
|
74
69
|
|
|
75
70
|
### Use cases
|
|
76
71
|
|
|
77
|
-
- Researching inside pi.
|
|
78
|
-
- Researching from Claude Code, Codex, or another coding agent while a cheaper or local model drives the run
|
|
79
|
-
-
|
|
80
|
-
- Building agent systems that find and read web content, or
|
|
72
|
+
- Researching inside pi. No API key needed.
|
|
73
|
+
- Researching from Claude Code, Codex, or another coding agent while a cheaper or local model drives the run. The main agent's budget stays untouched.
|
|
74
|
+
- Saving findings to a persistent, searchable knowledge store, scoped globally or per project.
|
|
75
|
+
- Building agent systems that find and read web content, or collecting a dataset of web sources.
|
|
81
76
|
|
|
82
77
|
### Why
|
|
83
78
|
|
|
84
|
-
-
|
|
85
|
-
-
|
|
86
|
-
-
|
|
87
|
-
-
|
|
79
|
+
- No quota and no monthly fee. Most AI search providers cap free searches and then charge, serving results from their own index. pi-research searches and scrapes locally through DuckDuckGo in a stealth browser.
|
|
80
|
+
- The index is local. Findings can be saved to a local [LanceDB](https://lancedb.com) knowledge store that seeds future runs. Repeat questions get faster and cheaper answers.
|
|
81
|
+
- Read-only by design. The research agent cannot run shell commands or write, edit, or delete anything. Prompt injection picked up mid-run has nothing to act on.
|
|
82
|
+
- Search a little or a lot. Depth levels range from a quick pass to a large-scale investigation.
|
|
88
83
|
|
|
89
84
|
### Requirements / limitations
|
|
90
85
|
|
|
@@ -92,12 +87,12 @@ Three depth levels (normal, deep, ultra) set the team size and number of rounds.
|
|
|
92
87
|
- An LLM with a 100k+ context window (an API key or a local model)
|
|
93
88
|
- Internet access on a residential IP, since search, scraping, and YouTube transcripts get bot-blocked from datacenter/VPS/cloud IPs
|
|
94
89
|
- pi. The pi extension uses the host's copy while the standalone CLI and agent skill install it as a dependency.
|
|
95
|
-
- Local knowledge-store embeddings need `@huggingface/transformers`,
|
|
90
|
+
- Local knowledge-store embeddings need `@huggingface/transformers`, an optional dependency. If its native image chain (sharp) cannot install, npm skips it with a warning and the install still succeeds, so everything works except local embeddings. The store tells you how to restore them.
|
|
96
91
|
- Cloudflare Turnstile and similar systems block scraping on some sites. A run compensates with a wide pool of search results to scrape.
|
|
97
92
|
|
|
98
93
|
### Channels
|
|
99
94
|
|
|
100
|
-
npm (`npm:@lincoln504/pi-research`) is the stable channel and is kept current with breaking pi changes. A git install is the development channel. It has the latest commits
|
|
95
|
+
npm (`npm:@lincoln504/pi-research`) is the stable channel and is kept current with breaking pi changes. A git install is the development channel. It has the latest commits and receives breaking changes first.
|
|
101
96
|
|
|
102
97
|
### License
|
|
103
98
|
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
name: pi-research
|
|
3
3
|
description: "Multi-agent web research for any coding agent. Use for anything requiring current information from the internet — news, trends, product/service/company facts, statistics, people, places, events, APIs, library behavior, or 'what is X / how does X work' questions. Also use to search a local knowledge store of previously researched findings before doing live research. Powered by the pi-research engine (search, stealth scraping, security databases, Stack Exchange). Not for reading local files, running project commands, or analyzing this repository's own source."
|
|
4
4
|
license: MIT
|
|
5
|
-
metadata: { "author": "Lincoln Deen", "version": "1.6.
|
|
5
|
+
metadata: { "author": "Lincoln Deen", "version": "1.6.15", "package": "@lincoln504/pi-research", "engine": "pi-research-sdk", "openclaw": { "requires": { "bins": ["node"] } } }
|
|
6
6
|
allowed-tools: Bash(node:*)
|
|
7
7
|
---
|
|
8
8
|
|
package/docs/CHANGELOG.md
CHANGED
|
@@ -7,6 +7,14 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
|
|
7
7
|
|
|
8
8
|
## [Unreleased]
|
|
9
9
|
|
|
10
|
+
### Changed
|
|
11
|
+
|
|
12
|
+
- **README: the recommended-model line is now the only bold text.** The Why-bullet lead-ins (No quota and no monthly fee / The index is local / Read-only by design / Search a little or a lot), the uninstall emphasis, and the optional-dependency emphasis are plain text now.
|
|
13
|
+
|
|
14
|
+
### Changed
|
|
15
|
+
|
|
16
|
+
- **README: full prose pass.** The recommended-model line is just the model name now. Semicolons became ordinary sentences, the staccato all-short-sentence draft was re-mixed into natural sentence rhythm, the How-it-works round loop is spelled out concretely (coordinator plans and starts the search, researchers scrape in parallel, the lead starts another round or writes the report), and the install/uninstall/use-cases/requirements sections were tightened.
|
|
17
|
+
|
|
10
18
|
## [1.6.14] - 2026-09-08
|
|
11
19
|
|
|
12
20
|
### Changed
|