Aimaghsoodi/foveance

Add shrink_anthropic() for Anthropic-shaped messages about 2 hours ago

enhancement good first issue

3

Cut your LLM token bill 60%+ without changing your code or your answers. Drop-in proxy + one-line Python API that auto-compresses agent context for Claude Code, Codex, OpenAI, Anthropic & Ollama. pip install foveance

Python

#ai-agents#anthropic#claude-code#codex#context-compression#cost-optimization#gpt#llm#llm-agents#llm-cost#llm-inference#ollama#openai#prompt-compression#proxy#python#rate-distortion#token-optimization

Ship a Docker image + one-line `docker run` for the proxy (publish to GHCR) about 2 hours ago

enhancement help wanted good first issue

Aimaghsoodi/foveance

3

Cut your LLM token bill 60%+ without changing your code or your answers. Drop-in proxy + one-line Python API that auto-compresses agent context for Claude Code, Codex, OpenAI, Anthropic & Ollama. pip install foveance

Python

#ai-agents#anthropic#claude-code#codex#context-compression#cost-optimization#gpt#llm#llm-agents#llm-cost#llm-inference#ollama#openai#prompt-compression#proxy#python#rate-distortion#token-optimization

Exact token counting via provider tokenizers (tiktoken / Anthropic) instead of chars/4 about 2 hours ago

enhancement help wanted

Aimaghsoodi/foveance

3

Cut your LLM token bill 60%+ without changing your code or your answers. Drop-in proxy + one-line Python API that auto-compresses agent context for Claude Code, Codex, OpenAI, Anthropic & Ollama. pip install foveance

Python

#ai-agents#anthropic#claude-code#codex#context-compression#cost-optimization#gpt#llm#llm-agents#llm-cost#llm-inference#ollama#openai#prompt-compression#proxy#python#rate-distortion#token-optimization

Compatibility sweep: verify Foveance with more agent CLIs (opencode, Crush, aider, OpenCLAW, Continue, Cursor) about 2 hours ago

help wanted good first issue compatibility

Aimaghsoodi/foveance

3

Cut your LLM token bill 60%+ without changing your code or your answers. Drop-in proxy + one-line Python API that auto-compresses agent context for Claude Code, Codex, OpenAI, Anthropic & Ollama. pip install foveance

Python

#ai-agents#anthropic#claude-code#codex#context-compression#cost-optimization#gpt#llm#llm-agents#llm-cost#llm-inference#ollama#openai#prompt-compression#proxy#python#rate-distortion#token-optimization

Integration: LangChain + LlamaIndex wrappers for shrink() about 2 hours ago

help wanted integration

Aimaghsoodi/foveance

3

Cut your LLM token bill 60%+ without changing your code or your answers. Drop-in proxy + one-line Python API that auto-compresses agent context for Claude Code, Codex, OpenAI, Anthropic & Ollama. pip install foveance

Python

#ai-agents#anthropic#claude-code#codex#context-compression#cost-optimization#gpt#llm#llm-agents#llm-cost#llm-inference#ollama#openai#prompt-compression#proxy#python#rate-distortion#token-optimization

Integration: LiteLLM callback/hook so Foveance shrinks context in any LiteLLM app about 2 hours ago

help wanted integration

Aimaghsoodi/foveance

3

Cut your LLM token bill 60%+ without changing your code or your answers. Drop-in proxy + one-line Python API that auto-compresses agent context for Claude Code, Codex, OpenAI, Anthropic & Ollama. pip install foveance

Python

#ai-agents#anthropic#claude-code#codex#context-compression#cost-optimization#gpt#llm#llm-agents#llm-cost#llm-inference#ollama#openai#prompt-compression#proxy#python#rate-distortion#token-optimization

Add a docs/examples notebook that runs shrink() against a real local model about 3 hours ago

enhancement good first issue

Aimaghsoodi/foveance

3

Cut your LLM token bill 60%+ without changing your code or your answers. Drop-in proxy + one-line Python API that auto-compresses agent context for Claude Code, Codex, OpenAI, Anthropic & Ollama. pip install foveance

Python

#ai-agents#anthropic#claude-code#codex#context-compression#cost-optimization#gpt#llm#llm-agents#llm-cost#llm-inference#ollama#openai#prompt-compression#proxy#python#rate-distortion#token-optimization

Support a ~/.foveance.toml config file for default budget/drift/upstream about 3 hours ago

enhancement good first issue

Aimaghsoodi/foveance

3

Cut your LLM token bill 60%+ without changing your code or your answers. Drop-in proxy + one-line Python API that auto-compresses agent context for Claude Code, Codex, OpenAI, Anthropic & Ollama. pip install foveance

Python

#ai-agents#anthropic#claude-code#codex#context-compression#cost-optimization#gpt#llm#llm-agents#llm-cost#llm-inference#ollama#openai#prompt-compression#proxy#python#rate-distortion#token-optimization

Open Issues Need Help