This release adds 6 notable features for engineering teams evaluating rollout.
Published 2mo
LLM Frameworks
✓ No known CVEs patched
✓ No known CVEs patched in this version
Topics
ai
ai-gateway
ai-governance
ai-proxy
ai-safety
ai-security
+14 more
ai-tools
anthropic
deepseek
litellm-alternative
llm
llm-gateway
observability
ollama
openai
openai-compatible-api
openai-proxy
opencode-zen
proxy
zhipu-ai
Summary
AI summaryInitial public release of Nenya, a high‑performance zero‑dependency Go AI gateway with secure request handling, dynamic provider discovery, Ollama Bouncer engine, circuit‑breaker/retry logic, token usage tracking, latency‑based auto‑reordering, Prometheus metrics and health checks.
Full changelog
- Initial public release of Nenya, a high‑performance, zero‑dependency Go AI gateway.
- Implements secure request handling with strict body size limits, header sanitization, and context‑aware timeouts.
- Dynamic provider discovery and model catalog merging for transparent multi‑provider routing.
- Ollama “Bouncer” engine for on‑the‑fly payload summarization and PII redaction when exceeding soft limits.
- Full circuit‑breaker and retry logic for resilient upstream communication.
- Per‑model token‑usage tracking and latency‑based auto‑reordering of providers.
- Prometheus metrics, health‑check endpoint, and structured slog output.
- Comprehensive GoDoc, Go standard‑library only, and passes all lint/formatting checks.
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About Nenya
All releases →Related context
Related tools
Beta — feedback welcome: [email protected]