vrr/spawn
2
0
Fork 0
mirror of https://github.com/OpenRouterTeam/spawn.git synced 2026-04-28 03:49:31 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 10

docs: Replace 'coding agent' with 'agents using remote API inference'

Browse source 
Clarifies that spawn agents use remote LLM APIs, not local inference,
which is why cheap CPU instances suffice and GPU clouds are unnecessary.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
B 2026-02-11 00:26:00 +00:00
parent ae7a999217
commit 3d0ac5e562
2 changed files with 7 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

4
CLAUDE.md
View file

@ -56,13 +56,13 @@ We bias heavily toward adding more clouds/sandboxes over more agents. To add one
4. Implement at least 2-3 agent scripts to prove the lib works
5. Update the cloud's `README.md`
**Good candidate clouds (cheap CPU compute for coding agents):**
**Good candidate clouds (cheap CPU compute for agents using remote API inference):**
- Container/sandbox platforms (fast spin-up, developer-friendly)
- Budget VPS providers with cheap small instances ($5-20/mo range)
- Regional providers with simple APIs (OVH, Scaleway, UpCloud)
- Any provider with REST API or CLI + SSH/exec + affordable pay-per-hour pricing
**DO NOT add GPU clouds** (CoreWeave, RunPod, etc.). Spawn runs coding agents that call LLM APIs — they need cheap CPU instances with SSH, not expensive GPU VMs.
**DO NOT add GPU clouds** (CoreWeave, RunPod, etc.). Spawn agents call remote LLM APIs for inference — they need cheap CPU instances with SSH, not expensive GPU VMs.
### 3. Add a new agent (only with community demand)