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
Merge pull request #8 from nicolabeghin/proxy-custom-openai-api-url
f5ffba6 Tejas Chopra committed 10 months ago
Merge pull request #6 from smartwatermelon/claude/docs-macos-deployment-20260119
18e01a0 Tejas Chopra committed 10 months ago
feat: add Docker configuration for containerized deployment
1b023e3 Nicola Beghin committed 10 months ago
fix(deployment): correct port placeholder in LaunchAgent plist template
063b6e8 Claude Code Bot committed 10 months ago
docs(deployment): add macOS LaunchAgent deployment guide and templates
3ac2620 Claude Code Bot committed 10 months ago
Add Phase 2 Progressive Summarization and fix Agno integration tests
4102402 chopratejas committed 10 months ago
Fix HeadroomAgnoModel to optimize tool outputs at invoke level
39a55b4 chopratejas committed 10 months ago
Implement COMPRESS_FIRST strategy for IntelligentContextManager
57b2de5 chopratejas committed 10 months ago
Add IntelligentContextManager for semantic-aware context management
14ecab6 chopratejas committed 10 months ago
Fix agno model.py mypy errors by declaring name and provider fields
f858451 chopratejas committed 10 months ago
Fix HeadroomAgnoModel to extend agno.models.base.Model and add real integration tests
67c927f chopratejas committed 10 months ago
Enhance /stats endpoint and add comprehensive benchmarks
77248cd chopratejas committed 10 months ago
Add TOIN field-level learning and comprehensive integration tests
dd832fe chopratejas committed 10 months ago
Use LiteLLM for model pricing instead of hardcoded values
09973b6 chopratejas committed 10 months ago