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

2e351c6
f18eba2
chore: sync plugin manifest versions
chopratejas committed 7 months ago
1b70e5c
e1694c7
247060c
2c9b072
test: clean up lazy provider export cache
JerrettDavis committed 7 months ago
535c4ac
style: match CI ruff formatting
JerrettDavis committed 7 months ago
8310a49
test: stabilize provider package init coverage
JerrettDavis committed 7 months ago
c8fc415
test: remove provider diff churn
JerrettDavis committed 7 months ago
4576f9c
docs: add codecov badge
JerrettDavis committed 7 months ago
f7e3450
docs: restore readme formatting
JerrettDavis committed 7 months ago
77af5aa
docs: add codecov badge
JerrettDavis committed 7 months ago
b4a1d4b
test: expand provider slice coverage
JerrettDavis committed 7 months ago
7831620
fix: fall back from stale persistent wrap manifests
JerrettDavis committed 7 months ago
ba45050
Merge upstream/main into feat/canonical-pipeline
JerrettDavis committed 7 months ago
88dc15e
style: ruff format compute_turn_id body
Garm committed 7 months ago
d88c1ab
af9af3d