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
fix: [BUG] A timeout in one image compression call resets the shared worker pool and affects concurrent requests (#4528)
e9bcfe7 Nandana Dileep committed 16 days ago
fix(opencode): only route POST requests to LLM endpoint paths (#4464)
336d462 CyberSprout committed 16 days ago
fix(diff): keep combined-diff changes made against a later parent (#4318)
4b788fd Jay Hemnani committed 16 days ago
fix(proxy): reconcile Chat content-block cache markers after prefix replay (#4333)
35ca9b8 tbartik committed 16 days ago
fix(cache): fail closed on SQLite corruption instead of deleting the store online (#4361)
9801833 yi111 committed 16 days ago
fix(memory): bound verb-pattern word runs to stop quadratic backtracking in bridge import (#4370) (#4376)
d232d09 viwe-monai committed 16 days ago
fix(proxy): forward Copilot accounting headers on streaming path (#4431)
66023a0 divyamnpll committed 16 days ago
docs: fix generate_report example arguments (#4435)
6cc0801 Anton Dziatkovskii committed 16 days ago
fix(docker): pass RUNTIME_HOME=/root for root bake targets (#4445)
670767e Younes Beriane committed 16 days ago
fix(proxy): route /v1/models to the x-headroom-base-url upstream (#4308)
6ef52c2 Younes Beriane committed 16 days ago
fix(ccr): keep proactive expansion out of the cached prefix (#4300)
b1f340e Matt Van Horn committed 16 days ago
fix(openclaw): record turn advancements as one marker file per key (#4212)
24acbe8 jedi-tal committed 16 days ago
fix(output-savings): rewrite a pre-rule ledger once instead of warning on every /stats poll (#4196)
96e81ac M Barry committed 16 days ago
fix(proxy): handle ClientDisconnect in anthropic_messages (#3532)
251d149 Bradley Allan Davis committed 16 days ago
fix(proxy): warm deferred kompress model so /health stops reporting backend=null (#2799)
e2350bc Parideboy committed 16 days ago
fix(wrap): route OMP OpenAI providers through Headroom (#2755)
fae1e84 Glen Jung committed 16 days ago
fix(backends): forward the standard service_tier param (litellm + anyllm) (#2468)
62cc38a Tejas Chopra committed 16 days ago
fix(proxy/memory): harden _extract_tool_calls against malformed choices and blocks (#2483)
effa5a5 Abhay Singh committed 16 days ago
fix(scripts): resolve hooks dir via git so install-git-hooks works in linked worktrees (#4176)
0f4275f aftabkh4n committed 16 days ago
fix(smart-crusher): preserve unchanged JSON bytes (#4044)
93279f3 Mansurshakh Japarov committed 16 days ago
fix(relevance): load the Rust default embedder from Python's pinned snapshot (#4190)
9bb4b13 Kenneth Wong committed 16 days ago
fix(backends/litellm): keep cache_control on text blocks for Bedrock prompt caching (#4565)
23a5bb1 Lucas Kim committed 16 days ago
fix(pipeline): store the pipeline input in CCR behind offload markers (#4576)
4d7765c Parideboy committed 16 days ago
fix(codec): reject densified blocks with mismatched row counts (#4271)
75df01d Andrew Barnes committed 16 days ago
fix(relevance): hand the embedding arena back after each run on macOS (#4567)
2363f83 gglucass committed 16 days ago
fix(privacy): turn off Mem0's PostHog telemetry by default (#4619)
fe69f38 Tejas Chopra committed 16 days ago