local-agentic-harness 0.7.1

A local-first, provider-neutral goal runner with a CLI, GUI, bounded tools, and deterministic review gates.

Agentic Harness

A coding agent saying “done” is not proof that the task is done.

Agentic Harness runs a coding agent on one project-local goal, preserves what it did, and refuses to accept completion until an independent command passes.

Quick Start

1. See the completion gate

pipx install local-agentic-harness
agentic-harness run-demo fix-tests /tmp/agentic-harness-demo --force

The packaged example starts with a failing test, runs the same goal engine, and ends only after the test passes. It is a controlled mechanics demo with a mock coding agent, not evidence about model quality. Its durable report is written to .agentic-harness/runs/<goal-id>/report.md. The complete under two minutes recording path is in the terminal demo script.

2. Use it on a real project

cd /path/to/your/project
agentic-harness selftest
agentic-harness gui

In Setup, choose an installed coding agent or compatible model and the command that independently proves the result. Enter one outcome and start. The browser shows the plan, checkpoints, changed files, checks, and final evidence.

The same configured workspace has a concise CLI path:

agentic-harness do "fix the failing tests and verify the result"
agentic-harness check
agentic-harness report

For a foreground autonomous run, use agentic-harness goal "..." and resume an interrupted durable goal with agentic-harness goal. Run agentic-harness quickstart to print the shortest path detected for the current project.

Product Boundary

local-agentic-harness is one Python distribution with a shared engine, project state model, packaged static browser assets, and two interfaces:

• agentic-harness is the CLI.
• agentic-harness-gui is the browser service.

This is the same install, not two products. Both interfaces use .agentic-harness/ inside the selected workspace. The portable embedded engine is the default; private controllers and machine-specific sidecars are not required.

Recipes

Common workflows have direct commands:

agentic-harness recipes
agentic-harness fix-tests
agentic-harness lint-fix
agentic-harness typecheck-fix
agentic-harness update-docs
agentic-harness changelog
agentic-harness verify-tests
agentic-harness run-recipe fix-tests --explain

Recipes auto-create config when a supported installed coding agent is available. Each run writes an operator-readable report at .agentic-harness/runs/<goal-id>/report.md.

How Completion Works

objective
   |
   v
plan -> act -> record progress -> evaluate -> repair if needed
                                      |
                                      v
                           independent verification
                                      |
                         pass --------+-------- fail
                           |                     |
                           v                     +--> continue or block
                     accepted done

The original objective remains attached to the goal across cycles and recovery. The worker maintains a plan, requirement audit, current subgoal, and checkpoint. Tool use produces durable redacted events. A completion claim is accepted only when every requirement resolves to a passed, current-run harness evidence record and at least one configured independent criterion passes. Worker-authored prose is not evidence. See the evidence contract.

Limits on cycles, elapsed time, model tokens, provider calls, and tool calls are resource budgets, not success conditions. Exhausting a budget produces a blocked or failed result; it never converts unfinished work into done.

One workspace has one active goal. Use separate project roots when truly independent goals must run concurrently.

Controlled Evaluation

A reproducible comparison has 24 task-behavior cases across six maintenance payloads. Each runs the same scripted coding-agent process directly and through Agentic Harness in pristine workspaces. The matrix includes correct first attempts, premature claims that can be repaired, persistent false claims, and process failures that can be retried.

Arm	Verified accepts	False accepts	Acceptance precision	Recovered tasks	Mean attempts
Direct baseline	6	12	33.3%	0	1.0
Agentic Harness	18	0	100%	12	2.0

This is a controlled gate evaluation, not a real-model benchmark or adoption claim. Its value is narrower: the direct baseline produced 12 false accepts; Agentic Harness produced 0 false accepts. It caught all 12 premature claims and recovered every repairable task at the explicit cost of more attempts. See the method, summary, and raw JSONL.

Execution Methods

Installed coding agents

The GUI can configure Codex, OpenCode, Aider, or CodeWhale. From the CLI, create or replace a starter config explicitly:

agentic-harness init-agent codex
agentic-harness init-agent opencode
agentic-harness init-agent aider
agentic-harness init-agent codewhale

The harness owns lifecycle, evidence, and independent review. The selected coding-agent process still owns its own credentials, tool permissions, and runtime policy. Safe-area labels are enforced by the embedded model agent; for an external coding-agent CLI they are operator guidance unless that CLI enforces the same boundary.

Local and cloud models

The embedded model agent accepts an exact OpenAI-compatible chat-completions endpoint and an arbitrary model ID. This covers local servers such as vLLM, llama.cpp, Ollama-compatible gateways, and LM Studio when they expose that API, as well as compatible cloud gateways.

Native Anthropic Messages and Google Gemini transports are not built into the embedded engine. Use an OpenAI-compatible gateway, an installed coding agent, or an optional external orchestrator if those native APIs are required.

The GUI is the recommended way to create a model profile. This equivalent cloud profile uses an environment-variable reference and contains no API key:

version: 1
worker: model_agent
llm:
  endpoint: https://provider.example/v1/chat/completions
  model: organization/model-name-or-any-provider-id
  api_key_env: MODEL_PROVIDER_API_KEY
  credential_source: env
  remote_data_confirmed: true
  max_steps: 8
  timeout: 120
review:
  command:
    - python
    - -m
    - pytest
    - -q
  command_timeout: 300
autonomy:
  max_cycles: 100
  max_elapsed_seconds: 7200
  max_total_tokens: 500000
  max_provider_calls: 200
  max_tool_calls: 1000

Set the key outside the project before running the CLI or GUI:

export MODEL_PROVIDER_API_KEY="use-your-secret-entry-path"
agentic-harness do "complete and verify one bounded goal"

Do not put a literal API key in .agentic-harness/config.yml. Model-agent config rejects plaintext keys. A session key entered in the loopback GUI stays only in that server process, is not returned by the API, and must be re-entered after restart. Environment-variable references survive restarts without writing the secret to project state.

Cloud profiles require HTTPS and remote_data_confirmed: true. That consent means selected file excerpts, tool observations, and prompts may leave the machine for the endpoint you chose. It is not inferred from the provider name.

Embedded Safety Boundary

The built-in model agent intentionally exposes a narrow tool set:

• list, read, and search workspace files;
• create text files and replace previously read text inside allowed paths;
• inspect Git status and diff;
• run only the verification commands supplied for the goal; and
• report a structured outcome with requirement evidence.

It does not expose arbitrary shell, delete, package-install, service-control, or network tools. Writes are contained to the workspace, protect repository and credential paths, reject symlink escapes, require a current file hash before replacement, and protect pre-existing dirty files unless they were explicitly placed in scope. Configured checks run in a minimal environment without provider keys or other unrelated process secrets. Provider redirects, URL credentials, URL query credentials, and oversized responses are rejected.

Transcripts and task events are redacted, written atomically, and stored with owner-only permissions. Redaction is defense in depth, not permission to place secrets in prompts or source files.

External coding-agent, shell, tmux, GitHub Actions, and optional orchestration adapters can have broader authority. Their tool policy is not silently upgraded to the embedded agent's enforcement; review their configuration before use.

GUI Operation and Network Safety

The GUI binds to loopback and asks the OS for a free port by default. Use the exact URL printed at startup:

agentic-harness-gui --project-dir /path/to/project --no-open

Choose a stable loopback port when a service or private reverse proxy needs one:

agentic-harness-gui --project-dir /path/to/project --port 8765 --no-open

Keep loopback as the default. A non-loopback bind is refused unless AGENTIC_HARNESS_GUI_TOKEN is set. Authenticated clients send that value in the Authorization: Bearer ... header; query-string tokens are not supported. If a reverse proxy uses another hostname, add only that expected hostname to AGENTIC_HARNESS_GUI_ALLOWED_HOSTS and preserve the original Host header.

See GUI deployment for the portable systemd and private network pattern.

Recovery and Evidence

Project configuration lives at .agentic-harness/config.yml. Goal state, redacted events, transcripts, reports, and verification evidence live below the same .agentic-harness/ directory.

After a failed or blocked goal, inspect agentic-harness report before deciding what to do next. Use agentic-harness restart to retry that same failed goal while preserving its evidence. Start a fresh goal only when the objective is intentionally separate.

GUI stop is cooperative: the current bounded tool step finishes, then the task is recorded as stopped. A late worker result cannot be accepted as done after cancellation. Session-only API keys are deliberately absent after a GUI process restart and must be entered again.

Optional Turnstone Integration

Turnstone is a separate, self-hosted orchestration framework. It is not bundled, imported, or installed by local-agentic-harness, and the default embedded GUI does not need it.

Operators who already run Turnstone may place an operator-maintained Turnstone-compatible wrapper behind the explicit local-goal backend:

export AGENTIC_HARNESS_LOCAL_GOAL=/absolute/path/to/compatible-wrapper
agentic-harness-gui --backend local-goal --project-dir /path/to/project --no-open

That path uses a narrow command contract and is opt-in. A direct Turnstone REST/SDK adapter is not part of this release. See Turnstone integration for the exact boundary, capability preflight, lifecycle expectations, and private-deployment note.

Other Adapters

The shared engine also supports shell, tmux, GitHub Actions, the legacy single-response local LLM adapter, and custom Python workers. See examples for project-local configurations and safety notes.

The small public API remains available:

from agentic_harness import Goal, Supervisor, Worker

Installation

Install the released distribution from PyPI:

pipx install local-agentic-harness

The distribution name avoids a collision with the unrelated agentic-harness package on PyPI. The installed CLI command remains agentic-harness. The same installation also provides agentic-harness-gui.

Install the current GitHub source with:

pipx install git+https://github.com/moortekweb-art/agentic-harness.git

For development:

git clone https://github.com/moortekweb-art/agentic-harness.git
cd agentic-harness
python -m venv .venv
. .venv/bin/activate
python -m pip install -e ".[test]"
python -m pytest tests/ -q

The GUI frontend ships as packaged static assets in the wheel and sdist. No Node, Electron, Tauri, or frontend build step is required to run it.

Release Verification

Before tagging a release:

python -m pip install -e ".[test]"
python -m pytest tests/ -q
python -m ruff check
python -m mypy agentic_harness
python -m compileall agentic_harness
python -m agentic_harness.cli release-smoke

release-smoke builds and checks a wheel and sdist, installs each into a fresh virtual environment, verifies both entry points and packaged assets, runs a goal/report smoke test, and writes SHA256SUMS beside the artifacts.

Documentation

• GUI architecture
• GUI design
• GUI deployment
• Autonomous goal contract
• Evidence contract
• Turnstone integration boundary
• Release checklist
• PyPI trusted publishing
• Security policy
• Contributor guide
• Examples

Contributing

Issues and pull requests are welcome. See CONTRIBUTING.md for setup, test, portability, documentation, and pull-request expectations. Security reports belong in the private channel described by SECURITY.md.

License

MIT. Copyright (c) 2026 Michael / Moortekweb. See LICENSE and AUTHORS.md.

Support

If Agentic Harness helps your local AI workflow, you can support the project at Buy Me a Coffee.