Skip to content
@heurema

heurema

Open-source AI agent tools. Craft, not conjuring.
README.md

heurema

Craft, not conjuring.

Open-source tools that make AI agent workflows auditable, bounded, and trustworthy.

Vision

AI agents act at machine speed. The discipline to govern them must be built in, not bolted on. heurema builds infrastructure for teams that delegate aggressively and verify everything.

Principles

  1. Discovery before automation. Find better work, not just faster work.
  2. Accountability is not delegatable. Agents execute. Humans own outcomes.
  3. Context is a product. Bad context produces confident wrong output.
  4. Tests are contracts. If a machine cannot enforce it, it is a suggestion.
  5. Silent autonomy is a defect. No audit trail means no work.
  6. Failure is never silent. It surfaces immediately and names an owner.
  7. Open source is a constraint. If it cannot be reviewed, it does not ship.

Tools

Tool What it does
signum Risk-adaptive development pipeline with adversarial consensus code review
herald Daily curated news digest — zero API keys, fully local
proofpack Proof-carrying CI gate for AI agent changes
arbiter Multi-AI orchestrator — Codex CLI + Gemini CLI for review, ask, implement, panel
teams-field-guide Comprehensive guide to Claude Code multi-agent teams
emporium Plugin marketplace — install any tool with one command

Install

claude plugin marketplace add heurema/emporium
claude plugin install signum@emporium

The measure of a heurema tool: when something goes wrong, you know exactly where, and exactly whose call it was.

Pinned Loading

  1. herald herald Public

    Daily curated news digest for your domain. Claude Code plugin. Zero API keys, fully local.

    Python 3

  2. signum signum Public

    Risk-adaptive development pipeline with adversarial consensus code review

    Shell 11

  3. arbiter arbiter Public

    1

  4. proofpack proofpack Public

    Proof-carrying CI gate for AI agent changes

    Python

Repositories

Showing 10 of 40 repositories
  • signum Public

    Risk-adaptive development pipeline with adversarial consensus code review

    heurema/signum’s past year of commit activity
    Shell 11 MIT 0 0 0 Updated Mar 27, 2026
  • snag Public

    Hit a snag? File it. Auto-detect project, check for duplicates, file GitHub issues on the right repo.

    heurema/snag’s past year of commit activity
    Rust 0 MIT 0 0 0 Updated Mar 25, 2026
  • reporter Public

    Issue reporter for heurema products. Claude Code plugin.

    heurema/reporter’s past year of commit activity
    Shell 1 MIT 0 0 0 Updated Mar 25, 2026
  • recon Public

    Agent-first context aggregator — pluggable reconnaissance for AI coding agents

    heurema/recon’s past year of commit activity
    Rust 0 0 0 0 Updated Mar 25, 2026
  • teams-field-guide Public

    Claude Code Agent Teams — Field Guide. Bugs, workarounds, orchestration patterns, ecosystem.

    heurema/teams-field-guide’s past year of commit activity
    0 MIT 0 0 0 Updated Mar 25, 2026
  • jj-supersede Public

    Detect function-level code supersession via jj predecessor chains + tree-sitter

    heurema/jj-supersede’s past year of commit activity
    Python 1 0 0 0 Updated Mar 25, 2026
  • proofpack Public

    Proof-carrying CI gate for AI agent changes

    heurema/proofpack’s past year of commit activity
    Python 0 MIT 0 0 0 Updated Mar 25, 2026
  • sift Public

    Signal over noise for humans and agents.

    heurema/sift’s past year of commit activity
    Go 0 0 0 0 Updated Mar 25, 2026
  • skillpulse Public

    Skill activation logging for emporium ecosystem

    heurema/skillpulse’s past year of commit activity
    Python 0 MIT 0 0 0 Updated Mar 25, 2026
  • sentinel Public
    heurema/sentinel’s past year of commit activity
    Shell 0 MIT 0 0 0 Updated Mar 25, 2026
View all repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…