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

deps: bump thiserror from 1.0.69 to 2.0.18 (#1519)
dependabot[bot] committed 4 months ago
e448d7b
deps: bump tower-http from 0.6.11 to 0.7.0 (#1520)
dependabot[bot] committed 4 months ago
98f7f1c
deps: bump toml from 0.8.23 to 1.1.2+spec-1.1.0 (#1517)
dependabot[bot] committed 4 months ago
6c705b4
Extract loop callback failure policy (#1977)
JD Davis committed 4 months ago
98842b8
Extract project name policy (#1974)
JD Davis committed 4 months ago
b5b59bc
2b09ece
fd0d29c
e92c253
Extract tool schema savings policy (#1971)
JD Davis committed 4 months ago
f843124
a617455
Extract Python forwarder mode policy (#1987)
JD Davis committed 4 months ago
70b98b6
0f846e5
b3a559b
82af5cd
Extract request limit policy (#1982)
JD Davis committed 4 months ago
69fd218
094a53c
b1e871d
740fb9b
ea19515
refactor(output): isolate savings policy (#1947)
JD Davis committed 4 months ago
c29b4ba