AI News HubLIVE
In-site rewrite3 min read

Bound – A deterministic control harness for AI agents

BOUND is a lightweight control harness that adds a deterministic evaluation step after each agent action, using observable evidence to decide whether to ACCEPT, RETRY, REPLAN, or ROLLBACK, preventing unnecessary refinement and regressions.

SourceHacker News AIAuthor: joopie-boy

Notifications You must be signed in to change notification settings

Fork 0

Star 1

BranchesTags

Open more actions menu

Folders and files

NameName

Last commit message

Last commit date

Latest commit

History

24 Commits

24 Commits

.github/workflows

.github/workflows

architecture

architecture

assets

assets

benchmarks

benchmarks

bound_integration

bound_integration

docs

docs

examples

examples

integrations

integrations

scripts

scripts

skills/bound

skills/bound

src/bound

src/bound

tests

tests

.gitignore

.gitignore

.pre-commit-config.yaml

.pre-commit-config.yaml

CHANGELOG.md

CHANGELOG.md

CONTRIBUTING.md

CONTRIBUTING.md

LICENSE

LICENSE

Makefile

Makefile

README.md

README.md

pyproject.toml

pyproject.toml

uv.lock

uv.lock

Repository files navigation

The deterministic control harness for AI agents.

Coding agents are good at continuing. They are less good at knowing when to stop.

BOUND sits between execution and the agent's next decision, turning observable evidence into a deterministic control signal:

ACCEPT · RETRY · REPLAN · ROLLBACK

Put BOUND in your agent

Install in ChatGPT / OpenAI Skills

Download BOUND-agent-skill.zip.

In ChatGPT, open Profile → Skills → Create → Upload from your computer.

Select the ZIP, review the scan result, and install the skill.

Start a new chat and invoke it with @BOUND, or let ChatGPT select it when your request matches the skill description.

The Skills menu must be available for your ChatGPT account or workspace. Personal Skills may need to be installed separately in ChatGPT on the web and in the desktop app because those installations do not automatically sync.

Install with skills.sh-compatible agents

BOUND includes an open SKILL.md skill for Codex, Claude Code, Cline, Kilo Code, and other compatible coding agents:

npx skills add Danny-de-bree/bound --skill bound

To install only for Codex without interactive selection:

npx skills add Danny-de-bree/bound --skill bound --agent codex -y

The skill lives in skills/bound/ and teaches the agent to install BOUND, establish meaningful evaluation boundaries, collect real evidence, report the numeric A/I/R/C/S/T calculation, and react to ACCEPT / RETRY / REPLAN / ROLLBACK.

Or use a paste-ready integration prompt

Choose your agent, open its integration prompt, and paste it into a new session:

Cline

Claude Code

Kilo Code

Hermes Agent

Any other agent

That's it.

The prompt tells the agent to install BOUND, inspect its workflow, identify meaningful evaluation boundaries, and wire the harness into its control loop.

For the initial setup, use your agent's strongest architecture or planning mode — or a stronger model if available. This first pass should focus on defining the plan, meaningful step boundaries, acceptance criteria, risks, budgets, and observable evidence.

Paste integration prompt into agent ↓ Agent installs BOUND ↓ Agent inspects project + workflow ↓ Agent defines goals, contracts, and evidence ↓ You review the integration plan ↓ Agent wires BOUND into the workflow ↓ Run your agent with BOUND

Once configured, the normal execution loop can use BOUND deterministically. No LLM judge is required for observable criteria.

The control loop

BOUND belongs after a meaningful execution step and before the agent decides whether to keep optimizing the same objective.

Agent executes ↓ Observable evidence ↓ BOUND evaluates ↓ ACCEPT / RETRY / REPLAN / ROLLBACK ↓ Agent changes its next action

Conceptually:

result = workflow.evaluate_step( contract=contract, evidence=evidence, criteria=criteria, )

match result.decision: case "ACCEPT": continue_to_next_step() case "RETRY": retry_current_approach() case "REPLAN": choose_new_strategy() case "ROLLBACK": rollback()

The agent still owns planning, reasoning, tool use, code changes, and execution.

BOUND decides whether the current result is good enough to move on.

Four decisions

Decision Meaning

ACCEPT Good enough. Stop optimizing this step and continue.

RETRY Keep the current approach and make one focused correction.

REPLAN Stop iterating on the current strategy and choose another approach.

ROLLBACK A hard risk boundary was exceeded. Return to a safe state.

BOUND can use observable evidence such as tests, lint and type checks, acceptance checks, expected changes, retries, tool calls, token usage, runtime, and rollback availability.

Good enough is enough. Keep progressing.

Why BOUND?

Without an explicit stopping policy, an agent can continue working after the task is already satisfactory:

task solved ↓ tests pass ↓ more refinement ↓ more calls and changes ↓ possible regression

BOUND adds an explicit control point:

task solved ↓ evidence collected ↓ BOUND evaluates ↓ ACCEPT ↓ continue to the next goal

BOUND does not replace the agent. It is a thin control harness around the agent's execution loop.

How it works

BOUND is the control harness.

Under the hood:

Contracts + evidence → evaluation layer BoundPolicy → deterministic decision engine BOUND → control harness Integration prompts → adoption layer

The scoring model, evidence mapping, thresholds, weights, calculations, and exact decision rules live in the technical documentation:

Read the architecture and scoring model →

Manual installation

If you want to integrate BOUND directly:

pip install bound-policy

Or:

uv add bound-policy

The PyPI distribution is bound-policy; the Python import and CLI are bound.

Current status

BOUND is experimental.

The scoring heuristics, weights, thresholds, and integration patterns still need broader validation on real agent workloads.

The next milestone is dogfooding BOUND inside real coding agents and measuring whether it reduces unnecessary post-solution work, calls, tokens, retries, and regressions without reducing task success.

Development

git clone https://github.com/Danny-de-bree/bound.git cd bound

uv sync uv run pytest uv run ruff check .

License

MIT © Danny de Bree

About

A deterministic control harness for AI agents. Know when to accept, retry, replan, or roll back.

pypi.org/project/bound-policy/

Topics

agents

harness-framework

llm-agents

agentic-coding

Resources

Readme

License

MIT license

Contributing

Contributing

Uh oh!

There was an error while loading. Please reload this page.

Activity

Stars

1 star

Watchers

0 watching

Forks

0 forks

Report repository

Releases 1

BOUND v0.6.0

Latest

Jul 17, 2026

Packages 0

Uh oh!

There was an error while loading. Please reload this page.

Contributors

Uh oh!

There was an error while loading. Please reload this page.

Languages

Python 99.7%

Makefile 0.3%