PyPI
cendorhq/cendor-libs
Production plumbing for LLM apps: context, cost, testing & governance — composable, framework-agnostic Python libraries.
Apache-2.02026年10月21日 · 指标 2.10.0
全部标签
目录标签
#llmops
公开记录中带有此标签的全部仓库——标签来自其 GitHub 主题或软件包注册表发布的关键词。健康度量遵循与记录其余部分相同的版本化方法论。
86 条记录
PyPI
ianarawjo/ChainForge
An open-source visual programming environment for battle-testing prompts to LLMs.
MIT2026年10月1日 · 指标 2.10.0
Go
dativo-io/talon
Control plane for company AI use cases — one self-hosted operating layer for shared budgets, policies, reliability, and session understanding, with verifiable evidence. EU-friendly: self-host, PII controls, data residency.
Apache-2.02026年9月10日 · 指标 2.10.0
Go · PyPI
anthony-chaudhary/fak
Agentic Runtime
Apache-2.02026年9月10日 · 指标 2.10.0
crates.io
bionic-gpt/bionic-gpt
Bionic is sovereign Agentic AI for the enterprise — Runs on-premise and can securely work with your sensitive data and systems.
Apache-2.02026年10月20日 · 指标 2.10.0
RubyGems
homemade-software-inc/completion-kit
Your prompts need tests too. Run prompts against real datasets, score outputs with LLM judges, version everything, and compare runs to see what got better.
自定义许可证2026年9月10日 · 指标 2.10.0
PyPI
xorbitsai/xrouter-llm
A prompt-aware LLM router that predicts which models can complete each request, then selects the cheapest capable one: 53.2% lower cost and +1.9 pts completion on our tested dataset.
自定义许可证2026年10月10日 · 指标 2.10.0
PyPI
atulkapoor/fde-framework
A framework for Forward Deployed Engineers: from problem statement to a deployable AI project — every decision traced to a fact, every fact to a source.
Apache-2.02026年9月19日 · 指标 2.10.0
PyPI · npm
manojmallick/gavio
The open standard AI gateway — PII protection, audit, reliability & cost control as composable interceptors. Same API in Python, Java & JavaScript.
MIT2026年9月11日 · 指标 2.10.0
Go
BaizeAI/kcover
🧯 Kubernetes coverage for fault awareness and recovery, works for any LLMOps, MLOps, AI workloads.
Apache-2.02026年9月12日 · 指标 2.10.0
PyPI · npm · Maven
hpnkv/a11
A streaming action runtime for AI agents, model serving, and multimodal APIs
Apache-2.02026年10月21日 · 指标 2.10.0
npm
inferock/inferock-bench
Local LLM cost-tracking proxy for OpenAI, Anthropic, Gemini, and pinned OpenRouter calls with token usage, failure, and billing-integrity receipts.
自定义许可证2026年9月14日 · 指标 2.10.0
PyPI · Go · npm
tonquoc0407/capybara
Terminal trace debugger for AI agents.
MIT2026年10月20日 · 指标 2.10.0
Go · npm
T4cceptor/centian
Give your AI agents structure, guardrails, and full observability — the Agent control plane built on MCP.
Apache-2.02026年9月19日 · 指标 2.10.0
PyPI
hanyeol/model-compose
Deploy production-ready AI services in minutes. One YAML file for agents, RAG pipelines, and MCP servers — run anywhere. Inspired by docker-compose.
MIT2026年9月18日 · 指标 2.10.0
Go · npm
Halleck45/promptcc
Cyclomatic complexity, but for LLM prompts. Static analysis that finds the business logic hidden in your prompts, scores it, and gates it in CI. Python, TypeScript, JavaScript, PHP.
MIT2026年9月19日 · 指标 2.10.0
Go
p0nymc1/cee
Deterministic-first execution engine for agent workflows in Go: the LLM extracts at the edge, a deterministic state machine decides. Zero dependencies, no-code JSON plugins, replayable runs.
Apache-2.02026年9月19日 · 指标 2.10.0
PyPI
AI-Hypercomputer/JetStream
JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).
Apache-2.02026年9月10日 · 指标 2.10.0
npm
jaein4722/Let-My-Agent-Sleep
Let AI agents start long-running jobs, stop polling, and resume the same session when the job finishes.
MIT2026年9月10日 · 指标 2.10.0
Go · npm · PyPI
Everton-baptista/agenteARQ
An open, versioned, verifiable standard for building AI agents — machine-readable manifests, guardrails, MCP allowlists and a CI release gate, shared across every AI coding assistant.
Apache-2.02026年9月20日 · 指标 2.10.0
Packagist
melaya-labs/melaya
Governed AI agents that actually do the work - in the cloud or on your own machine - across business systems, real browser tabs and real Android apps. Visual builder, MCP server, and official SDKs in 9 languages.
自定义许可证2026年9月18日 · 指标 2.10.0
PyPI
Root1V/argus-observability-platform
Production-grade observability and agentic AIOps for AI systems — OpenTelemetry-native across independent polyglot apps; GenAI semantic conventions with token/cost attribution; sub-2s detection on a hot path that skips the datastore; LLM agents that find root cause and notify. ClickHouse + Langfuse. 100% self-hosted — no vendor lock-in.
无许可证2026年10月4日 · 指标 2.10.0
Go
Mrg77/tfforge
An AI agent that builds, validates & secures Terraform — with a policy-as-code guard it can't bypass. Built from scratch on the Anthropic API.
MIT2026年10月19日 · 指标 2.10.0
Go
mutton-dev/raggate
Regression tests and quality gates for LLM/RAG pipelines — catch answer quality drops, latency regressions, and cost jumps in CI. Single Go binary.
MIT2026年10月19日 · 指标 2.10.0
npm
empirical-run/empirical
Test and evaluate LLMs and model configurations, across all the scenarios that matter for your application
MIT2026年9月8日 · 指标 2.10.0
PyPI
protectai/llm-guard
The Security Toolkit for LLM Interactions
MIT2026年9月17日 · 指标 2.10.0