Skip to main content
Glama
ismaelsoilet

jev-harness

by ismaelsoilet
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Related Servers

Alternatives to jev-harness

No user-submitted related servers found.

    Related Servers

    • MartinLoop — Stop Runaway

      Keesan12
      A
      license
      A
      quality
      A
      maintenance
      MartinLoop is the independent governance and financial control layer for AI coding agents. Set hard spend limits, prevent runaway loops, enforce verification, trigger rollback on failure, and generate auditable receipts showing what changed, what it cost, and whether the work passed.
      24
      981 npm
      409
      Apache 2.0

    • agent-guardrail

      ss1738
      A
      license
      Not graded
      quality
      A
      maintenance
      A runtime gate for coding agents. Blocks the tool calls that wreck a repo (force-push main, rm -rf, secret exfiltration, CI wipe) and lets normal build and commit work through. Machine-checked git-branch core (z3); the rest is high-precision heuristics. Tested on 3,790 real CI commands, 0 false blocks.
      1
      MIT
    • aperion-shield by AperionAI

      aperion-shieldofficial

      AperionAI
      F
      license
      A
      quality
      A
      maintenance
      Local guardrail proxy for AI coding agents. Wraps any MCP server (stdio or HTTP/SSE) and blocks destructive tool calls before they execute, with TOFU catalog pinning against rug pulls and tool-poisoning/result-injection scanning. Single Rust binary, Apache-2.0.
      14
      11
      -

    • Code Oracle

      wahyuzero
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables AI coding agents to verify code patches locally with sub-50ms neuro-symbolic analysis, detecting structural issues like dependency cycles and interface drift without consuming output tokens.
      1
      Apache 2.0

    • ctrl-alt-pray

      HoangYell
      A
      license
      B
      quality
      A
      maintenance
      Enables AI coding agents in Cursor, Claude Code, Cline, and similar editors to halt repetitive failed edits after two consecutive attempts and instead gather falsifiable evidence such as git status, dirty diffs, and locked-port checks before writing more code. It also supervises wrapped shell commands, terminating hung prompts and orphaned process trees so agents can restore a clean, testable baseline.
      3
      21 npm
      1
      ISC
    Deploy Server
    Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

    TDQS

    A4.4/5.0

    Scored across 6 tools

    Disambiguation5/5

    Each tool targets a distinct decision point in the agent workflow: triage failure, check abort, route task, verify completion, modulate reasoning, and evaluate nudge. The only potential overlap between route_task and modulate_reasoning_effort is well-clarified by descriptions that distinguish tier selection from per-call reasoning parameter mapping.

    Naming Consistency5/5

    All tool names follow a consistent jev_ prefix with snake_case verb_noun or verb_noun_noun structure (e.g., jev_triage_test_failure, jev_route_task). No deviations in style or convention.

    Tool Count5/5

    Six tools is well-scoped for an agent harness, with each tool addressing a unique decision point without redundancy. The set is neither too thin nor too heavy for the purpose.

    Completeness4/5

    The tools cover the core agent lifecycle decisions: model routing, reasoning effort, failure triage, abort detection, completion verification, and nudge evaluation. A minor gap exists in explicit state or attempt history management, but agents can work around this externally.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources