Commit Graph

1441 Commits

Author SHA1 Message Date
Dillon DuPont
c58ff55969 Added agent tool filtering agent-v0.4.31 2025-09-12 20:12:29 -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
2fdff0e566 Add Anthropic SDK as a dependency 2025-09-12 18:00:27 -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
ddupont
477612471e Merge pull request #408 from trycua/feat/eval-simplicity
Ignore extra computers when running evals
agent-v0.4.30
2025-09-12 14:52:20 -04:00
Dillon DuPont
fc0f10aaf9 Ignore extra computers when running evals 2025-09-12 14:50:18 -04:00
ddupont
71f0187edb Merge pull request #407 from trycua/fix/hud-pin
Pin HUD version
agent-v0.4.29
2025-09-12 14:00:34 -04:00
Dillon DuPont
ae22572658 Merge branch 'main' of https://github.com/trycua/cua 2025-09-12 13:58:22 -04:00
Dillon DuPont
fad293957d Pin HUD version 2025-09-12 13:57:28 -04:00
Dillon DuPont
cf95646503 Merge branch 'main' into models/opencua 2025-09-12 13:30:21 -04:00
Dillon DuPont
58807378dd Added internVL 2025-09-12 13:30:09 -04:00
Dillon DuPont
492ebe9f0e Added simple ollama agent example 2025-09-12 13:02:23 -04:00
ddupont
ab9cf0636b Merge pull request #405 from trycua/feats/hud-advanced
Fix errors when passing `tools=[]` and `trajectory_dir=...` to HUD runs
2025-09-12 12:59:44 -04:00
James Murdza
217f904f1f Merge pull request #406 from trycua/feat/hackathon-notebook
Hackathon notebook improvements
2025-09-12 12:58:28 -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
faf531825e Fixed error during response call 2025-09-12 12:32:03 -04:00
Dillon DuPont
b3040306b8 Fixing bugs 2025-09-12 12:06:36 -04:00
Dillon DuPont
b69943121d Fixed KeyError 2025-09-12 11:29:40 -04:00
Dillon DuPont
f795660f75 Upgraded HUD impl. to support custom tools 2025-09-12 11:14:03 -04:00
Dillon DuPont
2f28c3a2ce Added missing file agent-v0.4.27 agent-v0.4.28 2025-09-10 14:57:44 -04:00
ddupont
2dfc1e5095 Merge pull request #400 from trycua/docs/tips
Add simple guide for customizing computeragent
agent-v0.4.26
2025-09-10 12:21:32 -04:00
Dillon DuPont
ae6d35ffa5 Fixed broken link 2025-09-09 11:23:13 -04:00
Dillon DuPont
bae97a6cb7 Added message format documentation 2025-09-09 11:08:19 -04:00
Dillon DuPont
665e65cb85 Replaced computer shim with Docker computer 2025-09-09 11:00:52 -04:00
Dillon DuPont
b21c668946 added notebook 2025-09-09 10:58:37 -04:00
Dillon DuPont
f270af30e1 added notebook 2025-09-09 10:57:16 -04:00
Dillon DuPont
17d6709629 added simple guide for customizing computeragent 2025-09-09 10:55:57 -04:00
James Murdza
c38cab2776 Merge pull request #398 from trycua/feat/kasm-firefox 2025-09-08 18:26:16 -04:00
James Murdza
03b23a3fe7 Add Firefox to Ubuntu Docker image 2025-09-08 18:07:46 -04:00
James Murdza
c7a50433a5 Fix description of Kasm license 2025-09-08 18:00:23 -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
86b9096ae7 Merge pull request #397 from trycua/feat/link-docs-examples
Add references to standalone examples and notebooks
2025-09-05 11:30:20 -04:00
James Murdza
80153541fb Add references to standalone examples and notebooks 2025-09-05 11:29:33 -04:00
James Murdza
a6165a5a2d Merge pull request #396 from trycua/feat/hackathon-notebook
Add Jupyter notebook for the SOTA challenge
2025-09-05 11:28:21 -04:00
James Murdza
ba72f5840b Merge pull request #395 from trycua/fix/restore-developer-guide
Restore Developer Guide and add `pdm.lock`
2025-09-05 11:27:31 -04:00
ddupont
da9af2e0fd Merge pull request #390 from onel/reference-docs-20250901_145129
Reference documentation batch
computer-v0.4.5 agent-v0.4.25
2025-09-05 11:17:35 -04:00
James Murdza
c5ca6e9e9f Add Jupyter notebook for the SOTA challenge 2025-09-05 07:43:45 -04:00
James Murdza
ef37f266f5 Remove nonexistant example 2025-09-05 03:42:07 -04:00
James Murdza
26daf8f3da Fix links in READMEs 2025-09-05 03:31:01 -04:00
James Murdza
a578df75ab Add pdm.lock to project root 2025-09-05 03:31:01 -04:00