76 Commits

Author	SHA1	Message	Date
James Murdza	deb2132aef	Fix hackathon notebook	2025-09-13 03:20:08 -04:00
James Murdza	993d52527f	Rename hackathon notebook	2025-09-13 01:50:01 -04:00
James Murdza	981a081672	Improve notebook structure	2025-09-13 01:42:06 -04:00
James Murdza	8938b37ca7	Change hackathon notebook to use Docker	2025-09-13 01:42:05 -04:00
James Murdza	77d91ef6e1	Clarify instructions in hackathon notebook	2025-09-13 00:57:14 -04:00
James Murdza	4ec4bbc888	Add link to HUD integration documentation	2025-09-12 21:41:14 -04:00
James Murdza	3552ef62a8	Add relevant links to docs	2025-09-12 18:41:38 -04:00
James Murdza	73fb0002f0	Improve notebook structure	2025-09-12 18:36:56 -04:00
James Murdza	4c52aaa298	Assert that HUD_API_KEY is set	2025-09-12 18:27:34 -04:00
James Murdza	b72d8da8a7	Add Prequisites section	2025-09-12 18:13:16 -04:00
James Murdza	ea1caea73c	Reuse agent configuration for HUD evaluation	2025-09-12 18:00:27 -04:00
James Murdza	48e42d2334	Only load .env file in notebook directory	2025-09-12 18:00:27 -04:00
James Murdza	4b3e2077fb	Remove dataset size limit during HUD evaluation	2025-09-12 12:55:43 -04:00
James Murdza	68ecdcc99a	Assert Cua API keys exist in notebook	2025-09-12 12:55:22 -04:00
James Murdza	1aca043006	Automatically create .env file in notebook	2025-09-12 12:55:11 -04:00
James Murdza	28f206d824	Improve explanatory text in notebook	2025-09-12 12:54:50 -04:00
James Murdza	4dedd06c5b	Improve notebook structure	2025-09-12 12:39:37 -04:00
Dillon DuPont	665e65cb85	Replaced computer shim with Docker computer	2025-09-09 11:00:52 -04:00
Dillon DuPont	f270af30e1	added notebook	2025-09-09 10:57:16 -04:00
James Murdza	796835b9e5	Add trajectory viewer and VNC instructions to notebook	2025-09-08 09:53:42 -04:00
James Murdza	64b555bb34	Update notebook to use OSWorld-Tiny dataset	2025-09-08 09:53:42 -04:00
James Murdza	cd59a63a49	Fix URL in example notebook	2025-09-08 09:53:42 -04:00
James Murdza	c5ca6e9e9f	Add Jupyter notebook for the SOTA challenge	2025-09-05 07:43:45 -04:00
James Murdza	1882f099a2	Change HUD dataset name from OSWorld-Verified-XLang to OSWorld-Verified	2025-09-03 11:18:43 -04:00
James Murdza	c820d5124d	Load environment variables in HUD notebook	2025-09-02 16:10:13 -04:00
James Murdza	33ce7515a5	Clear HUD notebook outputs	2025-09-02 16:08:24 -04:00
Dillon DuPont	c4ce791a49	Update OSWorld output	2025-08-28 12:07:56 -04:00
ddupont	311bbf9709	Merge pull request #371 from trycua/chore/hud-upgrade ... [Agent] Upgrade HUD SDK to 0.4.12	2025-08-28 11:29:18 -04:00
Dillon DuPont	95cefc50f0	added extended kwargs, renamed callback to normalizer	2025-08-27 20:49:31 -04:00
Dillon DuPont	0d3f8ea3ff	Improved trajectory saving	2025-08-27 16:48:57 -04:00
Dillon DuPont	e8eaf66e2a	Added latest nb	2025-08-27 13:38:55 -04:00
Dillon DuPont	3c502354a8	added simple task id	2025-08-27 13:28:24 -04:00
Dillon DuPont	61a442da56	fixed getattr crash	2025-08-27 13:21:46 -04:00
James Murdza	afe01ff831	Add missing comma in example code	2025-08-27 12:53:55 -04:00
f-trycua	a6406ae179	Update notebooks for KASM Docker	2025-08-26 13:05:35 +00:00
James Murdza	69713ce677	Merge pull request #361 from onel/main ... Added a readme file to the notebooks folder	2025-08-23 22:41:28 -04:00
James Murdza	f9a317c190	Use correct return type for run_command	2025-08-21 19:13:28 -04:00
James Murdza	3b76612d66	Initialize computer before taking screenshot	2025-08-21 19:13:28 -04:00
James Murdza	33f81131d9	Fix variable name	2025-08-21 19:13:28 -04:00
James Murdza	141c9d3ad7	Fix out-of-date agent SDK code in notebook	2025-08-21 19:13:28 -04:00
James Murdza	b302a44ccf	Remove nonexistent script from computer server notebook	2025-08-21 19:13:28 -04:00
James Murdza	02e5e62591	Fix out-of-date agent SDK code in operator example	2025-08-21 19:13:28 -04:00
Andrei Onel	145a845232	Update README.md	2025-08-20 00:03:48 +03:00
copilot-swe-agent[bot]	8a51468162	Add README.md to notebooks folder explaining content and purpose ... Co-authored-by: onel <1862405+onel@users.noreply.github.com>	2025-08-19 19:38:15 +00:00
James Murdza	9a4c7215d8	Upgrade Claude 3.5 snapshot to a version with computer use support	2025-08-19 11:40:05 -04:00
Dillon DuPont	a60cf26bb8	Added last run	2025-08-12 12:00:35 -04:00
Dillon DuPont	8bbcbec54b	updated notebook	2025-08-08 19:46:19 -04:00
Dillon DuPont	5495529462	limited tasks in notebook	2025-08-08 18:26:44 -04:00
Dillon DuPont	f819c578b7	Add example notebook	2025-08-08 13:14:56 -04:00
James Murdza	d27ee728b5	Fix broken import after refactor in 5bfadf8f9a	2025-08-04 17:02:11 -04:00