agent-guardrails repositories

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

  1. 1
    agenttrailhq/guard

    Observability and guardrails for your ai agents. AgentTrail Guard traces your agent's execution and automatically compiles repeat failures into permanent guardrails.

    GitHub · TypeScript · 14 stars · 3 forks · +2 stars in 24 hours · Trending score 0.88

  2. 2
    Dataojitori/horon

    Executable memory & cognitive harness for AI agents. Let your agent learn, remember, and build its own guardrails.

    GitHub · Python · 31 stars · 2 forks · 0 stars in 24 hours · Trending score 0.34

  3. 3
    bitrouter/bitrouter

    elastic inference for your agentic workloads

    GitHub · Rust · 239 stars · 23 forks · 0 stars in 24 hours · Trending score 0.09

  4. 4
    renezander030/skillgate

    Deterministic finish-line gates for AI coding agents. A model-independent evaluator that blocks commit/publish until your definition-of-done passes. Works in opencode (any model), Claude Code, pre-commit and CI.

    GitHub · TypeScript · 10 stars · 1 forks · 0 stars in 24 hours · Trending score 0.04

  5. 5
    ucsandman/claude-harness

    The Claude Code harness I run every day, published under this name since day one and now the same repository as ucsandman/Agnostic-AI: guard hooks, rules, context modules, Mods, subagents, workflows, tools and jobs, ported to 20 clients. Zero-dependency Node.

    GitHub · JavaScript · 31 stars · 2 forks · 0 stars in 24 hours · Trending score 0.02

  6. 6
    SponsioLabs/Sponsio

    Deterministic safety solutions for probabilistic AI agents

    GitHub · Python · 455 stars · 27 forks · 0 stars in 24 hours · Trending score 0.00

  7. 7
    didvc/opencode-bwrap

    Run opencode inside a bubblewrap sandbox — confine AI file access to your current working directory

    GitHub · Shell · 20 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00

  8. 8
    nirholas/autopilot-mcp

    An AI agent's own autonomous-execution control plane over MCP — set autopilot scopes, a daily SOL spend cap, and auto-execute, then run the propose → execute → undo loop. The agent spends SOL and never sells $THREE. Authenticated, write-heavy; scope + spend enforcement is server-side.

    GitHub · JavaScript · 9 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00

  9. 9
    DevMortimer/pi-warden

    Guardrails for Pi that steer instead of interrupt: enforces your project rules on every write, holds only hard-to-undo actions (3 per 1,000 calls, measured on real sessions), catches unverified "done" claims and stuck loops, and trims tool output. Built on pi-typesafe.

    GitHub · TypeScript · 177 stars · 32 forks · 0 stars in 24 hours · Trending score 0.00

  10. 10
    Chaarangan/Stepgate

    Agents can't skip steps: an MCP server that runs gated, API-only stepfiles on the client's own model.

    GitHub · TypeScript · 13 stars · 2 forks · 0 stars in 24 hours · Trending score 0.00

  11. 11
    dgesteves/onsystem

    Keeps coding agents on your design system: catches palette colors, native elements and APIs your system lacks, at every edit and pull request, with the fix. Set it up once in your design-system package; every app in your monorepo gets it.

    GitHub · TypeScript · 26 stars · 4 forks · 0 stars in 24 hours · Trending score 0.00