@lincoln504/pi-research 1.6.13 → 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 +18 -23
- package/agent-skill/pi-research/SKILL.md +1 -1
- package/docs/CHANGELOG.md +17 -1
- 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
|
-
|
|
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 and
|
|
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 +7,20 @@ 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
|
+
|
|
18
|
+
## [1.6.14] - 2026-09-08
|
|
19
|
+
|
|
20
|
+
### Changed
|
|
21
|
+
|
|
22
|
+
- **README: the hero image (the two-parallel-runs screenshot from the pi extension page) is now the README's feature image.** The static frame extracted from the deleted GIF lasted one day; the bundled `docs/media/hero.png` — two simultaneous research runs with the per-researcher panels — is the image actually representative of the tool, and the now-unneeded `prompt-research.png` frame is removed.
|
|
23
|
+
|
|
10
24
|
## [1.6.13] - 2026-09-08
|
|
11
25
|
|
|
12
26
|
### Changed
|
|
@@ -17,6 +31,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
|
|
17
31
|
|
|
18
32
|
- **Dependency refresh, lockfile-only: `@earendil-works/*` 0.85.0→0.85.1 and `@typescript-eslint/*` 8.69→8.70.** Both are within the existing package.json ranges, so consumer installs are unaffected by the lockfile change itself — a fresh install already resolves 0.85.1 (verified by packing the tarball and installing it into a clean project: pi 0.85.1 resolves, the documented dual apache-arrow layout reproduces, `pi-research --help` boots). `PI_TESTED_MAX_VERSION` compares on major.minor only, so the patch stays inside the tested window with no warning. Deliberate holds unchanged: apache-arrow 21.1.0 (LanceDB IPC), playwright-core 1.60.0 (camoufox < 1.61), typescript < 6.1.0 (eslint peer ceiling).
|
|
19
33
|
|
|
34
|
+
- **README prose fixes: the last abstraction-speak is gone.** The "Read-only by design" bullet no longer claims the tool is "the right shape" for anything (a metaphor with no referent); it now states the two facts plainly: the research agent cannot run shell commands or write, edit, or delete anything, and prompt injection picked up mid-run has nothing to act on. "Breaks first" on the git-install channel is spelled out as "receives breaking changes first", and the model-recommendation line's stray em dash (the README was purged of them in the 1.6.9 cycle) is a colon now.
|
|
35
|
+
|
|
20
36
|
### Fixed
|
|
21
37
|
|
|
22
38
|
- **`npm ci` under npm 12 rejected the lockfile an `npm update` had rewritten** (this release cycle's own dep refresh): the rewrite dropped the `node-domexception@1.0.28` alias entry backing the `@nolyfill/domexception` override while leaving a stale real `node-domexception@1.0.0` copy nested under `@earendil-works/pi-coding-agent`. npm 11 (the local dev npm) accepted the tree; CI's npm 12 is stricter and failed every `npm ci --legacy-peer-deps` leg. The lockfile was regenerated with npm 12 itself, which collapses the stale nested copy so the override is the only resolution; `npm ci --legacy-peer-deps` now validates clean under both npm 11 and npm 12, and CI is green cross-OS.
|
|
@@ -27,7 +43,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
|
|
27
43
|
|
|
28
44
|
### Verified
|
|
29
45
|
|
|
30
|
-
- 3,064 unit tests over 242 files, ESLint clean, all four type-checks (TS 6 src + tests, TS 7 native src + tests), dependency-cruiser and madge clean (190 modules, no circular dependencies), build, and `npm ci --dry-run` manifest verification; `npm audit` reports 0 vulnerabilities. The packed tarball was installed into a clean project: pi 0.85.1 resolves fresh, the documented dual apache-arrow layout (21.1.0 nested / 18.1.0 hoisted for LanceDB) reproduces, and the installed CLI boots. CI green cross-OS (ubuntu ×2, macOS, Windows) including the consumer fresh-install and Arrow/LanceDB interop legs.
|
|
46
|
+
- 3,064 unit tests over 242 files, ESLint clean, all four type-checks (TS 6 src + tests, TS 7 native src + tests), dependency-cruiser and madge clean (190 modules, no circular dependencies), build, and `npm ci --dry-run` manifest verification; `npm audit` reports 0 vulnerabilities. The packed tarball was installed into a clean project: pi 0.85.1 resolves fresh, the documented dual apache-arrow layout (21.1.0 nested / 18.1.0 hoisted for LanceDB) reproduces, and the installed CLI boots. CI green cross-OS (ubuntu ×2, macOS, Windows) including the consumer fresh-install and Arrow/LanceDB interop legs. For this cycle additionally: the tarball installed and the CLI booted under npm 10, npm 11, and npm 12 alike, with the dual apache-arrow layout identical across all three.
|
|
31
47
|
|
|
32
48
|
## [1.6.11] - 2026-09-04
|
|
33
49
|
|