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

Fix tests
Garm committed 8 months ago
47d0e4d
.
Garm committed 8 months ago
af448a5
cb1c9ae
d1fe0d4
b4d2cb0
chore: bump version to 0.5.2
Tejas Chopra committed 8 months ago
b5631cd
.
Garm committed 8 months ago
a24daf3
chore: bump version to 0.5.1
chopratejas committed 8 months ago
62a5183
aa73c7b
chore: bump version to 0.5.0
chopratejas committed 8 months ago
b435d4b
test: add integration tests for token_headroom mode
chopratejas committed 8 months ago
2e8cb31
feat: add compression_cache stats to /stats endpoint
chopratejas committed 8 months ago
a9c14a5
feat: add token_headroom branch to OpenAI handler
chopratejas committed 8 months ago
3f2e483
feat: add token_headroom branch to Anthropic handler
chopratejas committed 8 months ago
e0d1050
603db75
feat: add HEADROOM_MODE config to ProxyConfig
chopratejas committed 8 months ago
73ccf25
feat: export CompressionCache from cache package
chopratejas committed 8 months ago
c125939