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
ci(init-native): install [proxy] extras and use pwsh for Windows shim check
bc7a95a JerrettDavis committed 7 months ago
test(init): make verbose stderr assertion click-version-agnostic
301563f JerrettDavis committed 7 months ago
ci: add init-native-e2e workflow across linux / macos / windows
0cfbc3f JerrettDavis committed 7 months ago
test(init): extend Docker e2e with bare/shim/per-subcommand cases
48e2431 JerrettDavis committed 7 months ago
Merge pull request #244 from gglucass/pr/harden-livez-backpressure-test
429e1d1 Tejas Chopra committed 7 months ago
Merge pull request #255 from JerrettDavis/fix/workflow-validation-retry-standalone
c821260 Tejas Chopra committed 7 months ago
Merge pull request #254 from JerrettDavis/fix/unwrap-codex-restores-config
ab0ee65 Tejas Chopra committed 7 months ago
chore(deps): bump nltk in the uv group across 1 directory
e25f551 dependabot[bot] committed 7 months ago
Merge pull request #247 from gglucass/fix/learn-prior-block-to-llm
8d4f21b Tejas Chopra committed 7 months ago
Merge pull request #248 from gglucass/fix/turn-id-strip-cache-control
f2c6e90 Tejas Chopra committed 7 months ago