agent-ultramode 0.1.1 → 0.1.2

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.
Files changed (2) hide show
  1. package/README.md +3 -3
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -14,11 +14,11 @@ And unlike most "add a verifier" posts, I benchmarked it before believing it. Th
14
14
 
15
15
  <video src="https://github.com/user-attachments/assets/134487dc-1d60-434b-a2dc-97cfd5942959" controls muted playsinline width="100%"></video>
16
16
 
17
- [▶ Watch the demo](https://github.com/maverick-tr/agent-ultramode/blob/main/ultramode.mp4) (55s, opencode + DeepSeek V4 Flash)
17
+ [▶ Watch the demo](https://github.com/user-attachments/assets/134487dc-1d60-434b-a2dc-97cfd5942959) (55s, opencode + DeepSeek V4 Flash)
18
18
 
19
19
  ## The receipts
20
20
 
21
- Benchmarked on **Terminal-Bench** with **DeepSeek V4 Flash 0731** as both the agent and the verifier, running inside **opencode** (N=5 attempts, same-model verifier). Verified end to end with both **OpenCode** and **Claude Code** as the agent (the numbers above are the OpenCode run; a Claude Code number will be added once benchmarked). Works with any agent, not just opencode.
21
+ Benchmarked on **Terminal-Bench** with **DeepSeek V4 Flash 0731** as both the agent and the verifier, running inside **opencode** (N=5 attempts, same-model verifier). Verified end to end with **OpenCode**, **Claude Code**, and **cline** as the agent (the numbers above are the OpenCode run; a Claude Code number will be added once benchmarked). Works with any agent, not just opencode.
22
22
 
23
23
  | Slice | base@1 (single shot) | ultra (best-of-N + verify) | oracle@5 (ceiling) |
24
24
  |---|:---:|:---:|:---:|
@@ -165,7 +165,7 @@ The 15 tasks were deliberately failure-skewed, so the +9 points is not what you
165
165
 
166
166
  - [x] **Standalone CLI** (`npx agent-ultramode`) so the loop runs anywhere, with any agent, no opencode required.
167
167
  - [x] **Multiple models in one pass** (repeatable `--agent`): spread attempts across different models, one neutral verifier picks the best.
168
- - [x] **OpenCode and Claude Code** verified end to end.
168
+ - [x] **OpenCode, Claude Code, and cline** verified end to end.
169
169
  - [ ] **First-class agent integrations** with tuned defaults, and a benchmark number, for Claude Code, Grok, Pi, and Codex.
170
170
  - [ ] Native slash-command or MCP packaging per agent. Contributions welcome.
171
171
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "agent-ultramode",
3
- "version": "0.1.1",
3
+ "version": "0.1.2",
4
4
  "description": "Best-of-N for coding agents with a same-model verifier: run your task N times in isolated git worktrees and apply the verified winner. A /ultra command for opencode.",
5
5
  "module": "ultra.ts",
6
6
  "main": "ultra.ts",