guardrails repositories

Trending repositories tagged guardrails, ranked by trending score. Updated daily.

  1. 1
    Makson179/Bello

    3x more usage on your coding agent, same quality. Have an multi-agent setup in mind? Bello already supports it. Mix models, run agents in parallel, have them check each other’s work, and reduce unnecessary model calls and noisy tool output. Turn on only what you need.

    GitHub · Python · 443 stars · 53 forks · +267 stars in 24 hours · Trending score 4.28

  2. 2
    maximhq/bifrost

    Open-source, high-performance AI gateway that works as your LLM gateway, MCP gateway and agent gateway. One OpenAI-compatible API for 10,000+ models, with failover, load balancing, semantic caching, virtual keys, budgets and MCP Code Mode. Works with any SDK or agent and adds under 200µs of overhead at 5k RPS.

    GitHub · Go · 9,944 stars · 1,646 forks · +98 stars in 24 hours · Trending score 3.89

  3. 3
    FailproofAI/failproofai

    Observability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement.

    GitHub · TypeScript · 10,018 stars · 580 forks · +99 stars in 24 hours · Trending score 3.83

  4. 4
    lennney/stop-that-shit

    Stop That Shit(别再造史了)|面向 Codex/GPT 场景的多平台 Hook + Skill Guard:拦截 AI coding agent 无需求的哈希、校验和与任务范围膨胀。 A multi-platform Hook + Skill Guard for AI coding agents in Codex/GPT workflows: stop unrequested hashes, checksums, and task-scope creep.

    GitHub · JavaScript · 4,046 stars · 85 forks · +87 stars in 24 hours · Trending score 3.48

  5. 5
    mauhpr/agentlint

    Local guardrails for AI coding agents. Check proposed file changes and shell commands, block risky patterns, and return actionable feedback. Works with Claude Code, Codex, Cursor, Gemini CLI, and more

    GitHub · Python · 190 stars · 13 forks · +49 stars in 24 hours · Trending score 2.89

  6. 6
    nizos/probity

    TDD enforcement and guardrails for Claude Code, Codex, and GitHub Copilot CLI

    GitHub · TypeScript · 251 stars · 33 forks · +30 stars in 24 hours · Trending score 2.52

  7. 7
    schalermthai/redproof

    Redproof: A Guardrails Harness for those who have trust issues.

    GitHub · TypeScript · 50 stars · 6 forks · +27 stars in 24 hours · Trending score 2.44

  8. 8
    vllm-project/semantic-router

    An open, programmable decision layer for models and compute.

    GitHub · Go · 6,515 stars · 1,143 forks · +10 stars in 24 hours · Trending score 2.44

  9. 9
    FuRongJun-1999/dsh-memory

    白箱AGI架构探索:元认知(自我认知循环)、持续学习(知识飞轮)、世界模型(条件空间+语义时空图)、自我改进(自举纪律)、零LLM白箱管线与可审计信任护栏。

    GitHub · Python · 731 stars · 72 forks · +15 stars in 24 hours · Trending score 2.40

  10. 10
    NVIDIA-NeMo/Guardrails

    NeMo Guardrails is an open-source library for applying programmable safety and security controls to LLM and agentic applications.

    GitHub · Python · 7,538 stars · 906 forks · +12 stars in 24 hours · Trending score 2.32

  11. 11
    OpenTradeOSS/OpenTrade

    The open-source trading harness for Claude Code / Codex agents.

    GitHub · TypeScript · 258 stars · 26 forks · +25 stars in 24 hours · Trending score 2.28

  12. 12
    kenryu42/cc-safety-net

    A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, DeepSeek Harness, Devin CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.

    GitHub · TypeScript · 2,087 stars · 100 forks · +8 stars in 24 hours · Trending score 2.14

  13. 13
    qkal/Canny

    Stops AI coding agents from claiming work is done without evidence. Deterministic hooks decide, TypeSafe's Jev advises. Append-only ledger, zero runtime dependencies.

    GitHub · TypeScript · 135 stars · 18 forks · +13 stars in 24 hours · Trending score 1.99

  14. 14
    BoundaryML/baml

    The programming language for agents

    GitHub · Rust · 9,530 stars · 523 forks · +7 stars in 24 hours · Trending score 1.94

  15. 15
    onlyreadai/onlyread

    Make AI browser agents read-only: a Chrome extension that refuses writes (send, post, edit, delete) before they leave the browser.

    GitHub · TypeScript · 109 stars · 13 forks · +6 stars in 24 hours · Trending score 1.90

  16. 16
    agentcontrol/agent-control

    Centralized agent control plane for governing runtime agent behavior at scale. Configurable, extensible, and production-ready.

    GitHub · Python · 340 stars · 58 forks · +11 stars in 24 hours · Trending score 1.87

  17. 17
    future-agi/future-agi

    Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.

    GitHub · Python · 2,285 stars · 725 forks · +4 stars in 24 hours · Trending score 1.78

  18. 18
    cuga-project/cuga-agent

    CUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable architecture, reasoning modes, and policy-aware features.

    GitHub · Python · 1,193 stars · 215 forks · +3 stars in 24 hours · Trending score 1.76

  19. 19
    ZaxbyHub/opencode-swarm

    Architect-centric agentic swarm plugin for OpenCode. Hub-and-spoke orchestration with SME consultation, code generation, and QA review.

    GitHub · TypeScript · 539 stars · 62 forks · +5 stars in 24 hours · Trending score 1.64

  20. 20
    theopenco/llmgateway

    Route, manage, and analyze your LLM requests across multiple providers with a unified API interface.

    GitHub · TypeScript · 1,755 stars · 201 forks · +6 stars in 24 hours · Trending score 1.64

  21. 21
    Singularity-Compute/super-decider

    Decisions, not essays: a choice, a yes or no, or a score with a calibrated probability. Open weights, Jev-compatible API, adaptive thinking.

    GitHub · Python · 19 stars · 0 forks · +10 stars in 24 hours · Trending score 1.64

  22. 22
    mokevnin/dev-quality-gates

    An opinionated, curated list of tools for enforcing software development standards: one recommended tool per job, with limits.

    GitHub · Python · 395 stars · 24 forks · +3 stars in 24 hours · Trending score 1.55

  23. 23
    lawrence3699/jev-style

    JevStyle: local decision models for AI agents. Classify, route and score with a probability per option. systemone-compatible local server, MCP tools, Claude Code guard. Open weights, Apache-2.0.

    GitHub · Python · 138 stars · 4 forks · +1 stars in 24 hours · Trending score 1.47

  24. 24
    Cygnux-Labs/Tracekit

    Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.

    GitHub · Python · 799 stars · 131 forks · −12 stars in 24 hours · Trending score 1.46