Skip to content

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

Commits on main

47e734c
4d8b76f
test(proxy): cover codex responses subpath aliases
JerrettDavis committed 7 months ago
eb302fa
fix(proxy): alias nested codex responses routes
JerrettDavis committed 7 months ago
2ceceb4
fix(openclaw): launch Windows headroom shims via shell
JerrettDavis committed 7 months ago
afb3390
chore: apply ruff formatting
JerrettDavis committed 7 months ago
9c1bef5
0da1a7b
fix(openclaw): preserve upstream response paths
JerrettDavis committed 7 months ago
8134939
fix(openclaw): wait for proxy before gateway routing
JerrettDavis committed 7 months ago
621c3b6
fix(openclaw): keep gateway routing runtime-only
JerrettDavis committed 7 months ago
e038367
feat(openclaw): support configurable gateway providers
JerrettDavis committed 7 months ago
6f500df
docs(openclaw): document codex gateway routing
JerrettDavis committed 7 months ago
a4fe13d
fix(openclaw): route codex through headroom proxy
JerrettDavis committed 7 months ago
92b7b09
059e165
c92a6b9
Bump to v0.5.21
chopratejas committed 7 months ago
9c51f63
addcfcf
fix(ci): match proxy formatting to Ruff 0.15.9
JerrettDavis committed 7 months ago
710ef8d
fix(ci): harden wrap e2e validation
JerrettDavis committed 7 months ago
ca728a4
fix: skip token inflation guard in cache mode
Tejas Chopra committed 7 months ago
1006bc3