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

ci: add Windows wheel build job (win_amd64) (#1086)
sgfdhgfnjgmhgmnfd657-sys committed 4 months ago
48f06ca
cb38f79
0ce09fb
fd5b9e7
1f3696a
Extract request log redaction policy (#1968)
JD Davis committed 4 months ago
88e41b6
fix: harden persistent install startup (#1851)
JD Davis committed 4 months ago
1d2b76e
fix: patch nltk vulnerability (CVE-2026-54293) (#1929)
OrbisAI Security committed 4 months ago
28ca61f
[codex] Document local LLM prefill benchmarking (#1396)
panamarob30-jpg committed 4 months ago
abc557a
98ff203
test(litellm): remove unused pytest import
JerrettDavis committed 4 months ago
8527b91
ci: preserve merge labels while state is unknown
JerrettDavis committed 4 months ago
2d41833
ci: keep ready label off changes-requested PRs
JerrettDavis committed 4 months ago
595b709
772adc9