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.
Python agentaianthropicclaude-codecompressioncontext-engineeringcontext-windowcursorfastapilangchainllmmcpopenaiprompt-engineeringproxypythonragtoken-optimizationtokenstypescript
Commits on main
deps: bump toml from 0.8.23 to 1.1.2+spec-1.1.0 (#1517)
6c705b4 dependabot[bot] committed 4 months ago
fix(proxy): handle ClientDisconnect in passthrough body reads (#2033)
9db8a6b GUOHAO LIU committed 4 months ago
test(memory): skip decorators on offline model misses (#2020)
4e19bcf JD Davis committed 4 months ago
fix(kompress): surface model-not-ready state via logs and health endpoint (#2034)
12aa2cb GUOHAO LIU committed 4 months ago
fix(cache/semantic): key entries by context hash, not query text (#2022)
d8783ab Abhay Singh committed 4 months ago
fix(transforms/code): coerce language aliases instead of raising (#1975)
27ddde1 Abhay Singh committed 4 months ago
fix(models): version-boundary longest-prefix match in ModelRegistry.get (#1658)
b699bed Abhay Singh committed 4 months ago