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
Release v0.6.0: cross-agent memory, plugin learn, code graph
0f7f7b0 chopratejas committed 7 months ago
Fix tests: update default assertions for disabled CodeCompressor
b0ed0de chopratejas committed 7 months ago
Merge pull request #130 from Gyeonghun-Park/feat/cli-llm-backend
a245234 Tejas Chopra committed 7 months ago
Merge pull request #136 from JerrettDavis/jd/openclaw-launch-fix
12adb8e Tejas Chopra committed 7 months ago
Merge pull request #139 from JerrettDavis/feat/docker-native-cli
9f124c9 Tejas Chopra committed 7 months ago
Merge pull request #141 from JerrettDavis/feat/copilot-wrap
fb953eb Tejas Chopra committed 7 months ago
feat(cli): add Docker-native install flow and parity docs
38b1483 JerrettDavis committed 7 months ago
Merge remote-tracking branch 'origin/main' into feat/cli-llm-backend
da4b971 Gyeonghun Park committed 7 months ago
Fix CodeAwareCompressor: statement-based truncation, docstring fix
1ccab7d chopratejas committed 7 months ago
Merge pull request #131 from JerrettDavis/jd/healthchecks
f15ef78 Tejas Chopra committed 7 months ago
Merge pull request #132 from JerrettDavis/jd/devcontainers
5b81395 Tejas Chopra committed 7 months ago