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
Add HTMLExtractor for web content extraction with OSS benchmarks
d1a2832 chopratejas committed 9 months ago
Merge pull request #16 from chopratejas/feature/strands-integration
986adae Tejas Chopra committed 9 months ago
Update README with dashboard info and installation recommendations
f3e03f1 chopratejas committed 9 months ago
Fix Bedrock backend: use inference profiles for Claude 4+ models
8128c92 chopratejas committed 9 months ago
Merge pull request #13 from chopratejas/feature/memory-cli
f89c12d Tejas Chopra committed 9 months ago
Merge pull request #12 from chopratejas/feature/bedrock-backend
0f2a0d9 Tejas Chopra committed 9 months ago
Fix mypy errors and add network timeout handler for flaky CI tests
52da662 chopratejas committed 9 months ago
fix: improve error handling and add comprehensive test coverage
d329836 chopratejas committed 9 months ago
docs: update documentation for IntelligentContext TOIN + CCR integration
83c0334 chopratejas committed 9 months ago
feat(toin): add TOIN + CCR integration to IntelligentContextManager
fef02fa chopratejas committed 9 months ago
feat(toin): extend TOIN integration to all ContentRouter compression strategies
4f9a3d1 chopratejas committed 9 months ago
feat(proxy): add connection pooling, HTTP/2, and multi-worker support
7c6d713 chopratejas committed 9 months ago
feat: add streaming memory tool support with credential error handling
9825d99 Tejas Chopra committed 9 months ago
fix: correct cost calculation for cache tokens and simplify memory DevEx
787f925 Tejas Chopra committed 9 months ago
Add hierarchical memory system with graph + vector storage
da74341 chopratejas committed 9 months ago