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
Remove obsolete Ruff UP038 ignore to stabilize CI lint output
0a8254d JerrettDavis committed 7 months ago
Harden cache-mode immutability for OpenAI and fix stats mode reporting
2625789 JerrettDavis committed 7 months ago
Rebrand proxy modes to token/cache and harden cache-mode stability
54419ad JerrettDavis committed 7 months ago
Merge remote-tracking branch 'upstream/main' into fix/anthropic-prefix-cache-stability
d78fdfe JerrettDavis committed 7 months ago
Harden Anthropic prefix cache stability across proxy and batch paths
7d02829 JerrettDavis committed 7 months ago
refactor(docker): migrate to bake with multi-variant distroless images
63aebe8 pratikbin committed 7 months ago
Fix headroom learn writing ~/CLAUDE.md instead of ~/.claude/CLAUDE.md
4bd778f chopratejas committed 7 months ago
Fix remaining review issues: null safety, compressed count, batch tokens
7f84965 chopratejas committed 7 months ago
Disable image compression until token counting is accurate
da2fe3a chopratejas committed 7 months ago
Fix code review issues: batch NameError, null safety, token types
af418a2 chopratejas committed 7 months ago
Merge pull request #98 from JerrettDavis/hotfix/openclaw-toolcall-stream-linkage
f984021 Tejas Chopra committed 7 months ago
Merge pull request #100 from JerrettDavis/feat/wrap-openclaw-bootstrap
43f7398 Tejas Chopra committed 7 months ago
fix(cli): default wrap openclaw spec to headroom-ai/openclaw
61dacc9 JerrettDavis committed 7 months ago