Scrub model names + GitHub refs + license

README.md

@@ -6,9 +6,6 @@ colorTo: gray
 sdk: static
 pinned: true
 short_description: Recursive Language Model CLI on Cloudflare Workers.
-models:
-  - moonshotai/Kimi-K2-Instruct
-  - google/gemma-2-27b-it
 tags:
   - recursive-language-models
   - agentic-coding
@@ -18,7 +15,7 @@ tags:
   - arxiv:2512.24601
 ---
 
-HotCopy is a Recursive Language Model CLI on Cloudflare Workers. Unbounded context, agent swarms in parallel, two-model architecture (Kimi K2.6 orchestrator + Gemma 4 workers, 256K context each), no API keys, no config.
+HotCopy is a Recursive Language Model CLI on Cloudflare Workers. Unbounded context, agent swarms in parallel, two-tier orchestrator/worker architecture (256K context per agent), no API keys, no config.
 
 <div class="hc-org-card">
   <style>
@@ -97,7 +94,6 @@ HotCopy is a Recursive Language Model CLI on Cloudflare Workers. Unbounded conte
   <p class="hc-tagline">Your codebase is too big for any context window. <em>So we killed the context window.</em> Managed recursive AI coding CLI — agent swarms decompose impossible problems in parallel.</p>
   <div class="hc-cta-row">
     <a class="hc-cta hc-cta-primary" href="https://hotcopy.ai">Install</a>
-    <a class="hc-cta hc-cta-secondary" href="https://github.com/hotcopyai/hotcopy">GitHub</a>
   </div>
   <div class="hc-meta">▸ UNBOUNDED CONTEXT // 50+ PARALLEL AGENTS // 0 API KEYS</div>
 </div>
@@ -124,7 +120,7 @@ Median RLM cost ≤ base model cost; up to 3× cheaper than summary-agent baseli
 ## How it works
 
 - **Prompt as environment.** Project context is loaded into Durable Object memory as REPL variables. The orchestrator sees only metadata (file count, repo map, total chars) — never raw files.
-- **Two-model architecture.** Kimi K2.6 (`@cf/moonshotai/kimi-k2.6`) is the RLM root model with a 256K context window. Gemma 4 (`@cf/google/gemma-4-26b-a4b-it`) is every sub-call worker, also 256K, with vision.
+- **Two-tier orchestrator/worker architecture.** The RLM root model owns a 256K orchestration window. Every sub-call routes to a separate worker model with its own 256K window and multimodal capability — managed for you, no provider keys to wire up.
 - **REPL with stdout truncation.** The orchestrator writes JavaScript that runs in a sandboxed V8 isolate (`@cloudflare/codemode`). Stdout is truncated before being appended to history — variables hold the long state, the model history holds the metadata.
 - **Parallel sub-calls via `llm_batch()`.** Unlike the paper's sequential implementation, HotCopy fans out scouts in parallel through Cloudflare Workers, dramatically reducing latency on map-reduce decompositions.
 - **Durable Objects + AI Gateway.** Every model call routes through `hotcopy-gateway` for cost tracking, prefix caching (per-session affinity), and rate-limit handling. State lives in DO SQL — trajectories, sub-calls, costs, all logged for debugging.
@@ -170,7 +166,7 @@ Cloudflare Workers + Agents SDK · Durable Objects (RLMOrchestrator, WorkerAgent
 npm i -g hotcopy && hotcopy
 ```
 
-Auth with GitHub on first run. No API keys. No config files. Managed inference is included.
+Sign in on first run. No API keys. No config files. Managed inference is included.
 
 ## What we publish on Hugging Face
 
@@ -228,11 +224,6 @@ Auth with GitHub on first run. No API keys. No config files. Managed inference i
     <span class="hf-title">hotcopy.ai</span>
     <span class="hf-sub">Product site</span>
   </a>
-  <a class="hf-card" href="https://github.com/hotcopyai/hotcopy">
-    <span class="hf-emoji">💻</span>
-    <span class="hf-title">GitHub</span>
-    <span class="hf-sub">Source + issues</span>
-  </a>
   <a class="hf-card" href="https://arxiv.org/abs/2512.24601">
     <span class="hf-emoji">📄</span>
     <span class="hf-title">Paper</span>
@@ -242,4 +233,4 @@ Auth with GitHub on first run. No API keys. No config files. Managed inference i
 
 ---
 
-License: MIT. Contact: hello@hotcopy.ai · [hotcopy.ai](https://hotcopy.ai)
+Contact: hello@hotcopy.ai · [hotcopy.ai](https://hotcopy.ai)