HarnessMatch

Search 73 product records by name, workflow, interface, or documented capability.

Quick access
Use ↑ ↓ to move, Enter to open, Esc to close.

Quick access links shown.

Menu

Coding agent

Plandex

Dormant self-hosted planner for large changes with diff review and rewind.

Status
Dormant
License
MIT
Evidence
Documented + code-verifiable, 25 sources
Product record checked
2026-07-27
Compare harnessesInspect sources

At a glance

An MIT-licensed terminal coding agent whose last public release was July 2025. Its maintained-era design combined persistent plans, project maps, model-role packs, cumulative diff review, command debugging, and rewind; the hosted cloud later wound down, so the remaining path is a dormant self-hosted codebase.

Good choice if

  • Existing self-hosters preserving a plan-based workflow for large changes
  • Researchers studying persistent context, model-role routing, and diff-first review
  • Teams evaluating migration paths from an older Plandex installation

Check before choosing

  • Plandex Cloud stopped accepting users in October 2025; the repository has had no later commit, and the linked docs and installer domains were unavailable when checked
  • The cumulative diff sandbox separates proposed files, but commands run on the host; Linux process grouping is best-effort and explicitly falls back to no isolation, while other operating systems use none
  • The default semi-autonomous mode asks before command execution, but full mode can auto-apply, auto-execute, and auto-debug potentially destructive commands
See 3 more considerations
  • The CLI supports scripting and non-interactive flags, but there is no documented CI contract, machine-readable output mode, MCP implementation, or delegated subagent runtime
  • The repository contains six Go test files and an unfinished Promptfoo proof of concept whose metrics are marked coming soon; no independent Plandex benchmark or direct scientific evaluation was found
  • Ollama is supported only with self-hosting, and the project warns that its all-local pack is experimental rather than recommended for real work

Capability support

Documented first-class product support, checked against the sources below.

External tools (MCP)
Not documentedNo first-class support established by the current recordAbsence of current documentation is not proof that the capability is impossible.
Reusable skills
Not documentedNo first-class support established by the current recordAbsence of current documentation is not proof that the capability is impossible.
Local models
DocumentedLocal or self-hosted model pathSource · checked 2026-07-27The source establishes the mechanism, not its quality or availability in every mode.
Agent parallelism
Not documentedNo first-class support established by the current recordAbsence of current documentation is not proof that the capability is impossible.
Runs without an open UI
DocumentedNon-interactive or automation surfaceSource · checked 2026-07-27The source establishes the mechanism, not its quality or availability in every mode.
Browser control
DocumentedBuilt-in or product-supported browser controlSource · checked 2026-07-27The source establishes the mechanism, not its quality or availability in every mode.
Isolated execution
Not documentedNo first-class support established by the current recordAbsence of current documentation is not proof that the capability is impossible.
Undo file changes
DocumentedProduct-supported file or session rollbackSource · checked 2026-07-27The source establishes the mechanism, not its quality or availability in every mode.

Getting started

For an existing or archival deployment, use the v2.2.1 GitHub release or build the CLI from source, start the Docker Compose server, configure provider credentials, and review pending diffs before applying. Do not rely on the repository's old plandex.ai installer URL.

Open official documentation

Classification and operating model

Category fit and technical mechanisms are evidence records, not product-quality scores.

Category fit
Qualifies, 4/4 criteria
Operating model
7/7 layers documented
Inspect category criteria and operating mechanismsFirst-party records

Why it qualifies as a coding harness

This confirms category fit, not product quality. Every required criterion links back to first-party evidence.

Qualifies4 of 4 required criteria evidenced

  • Adaptive agent loop

    Documented

    The system repeatedly observes results and chooses the next action instead of following a fixed one-pass graph.

    EvidenceRepository snapshot and lifecycle notice

  • Repository tool execution

    Documented

    The system can use tools to inspect and change a repository or its execution environment.

    EvidenceExecution and debugging

  • Task-aware context management

    Documented

    The runtime assembles, updates, compacts, retrieves, or persists task-relevant context while work proceeds.

    EvidenceContext management

  • Model-independent runtime control

    Documented

    Permissions, budgets, interruption, policy, or stop controls operate outside the model's own text generation.

    EvidenceAutonomy levels

Membership establishes category fit only. It does not score quality, safety, autonomy, model capability, or benchmark performance. · Read the membership rule.

How it works under the hood

Seven mechanisms mapped from first-party records. These labels describe what the harness provides, not how intelligent its model is.

7/7layers documented
  • Execution & isolationHost processDocumented mechanism, not a performance score.
  • Tooling & integrationsBuilt-in toolsDocumented mechanism, not a performance score.
  • Context & statePersistent stateDocumented mechanism, not a performance score.
  • Lifecycle & recoveryCheckpoint/rewindDocumented mechanism, not a performance score.
  • ObservabilitySession onlyDocumented mechanism, not a performance score.
  • VerificationTool-assistedDocumented mechanism, not a performance score.
  • Governance & permissionsApproval promptsDocumented mechanism, not a performance score.

Measured and public context

Configuration-specific measurements and source-native activity stay separate from general product capability.

Inspect code audit, measured configurations, and ecosystem signalsContext, not a product score

Public code audit

2/5public artifacts present
Security policy
Not found
CI workflow
Not found
Automated tests
Present at inspected commit
Evaluation assets
Present at inspected commit
Contributor documentation
Not found

The dormant tree has six Go test files and an unfinished Promptfoo proof of concept, but no SECURITY.md disclosure policy, broad test CI, root contributor guide, complete evaluation metrics, immutable result record, or independent task benchmark.

Inspect commit e2d772072efadbe41d2946d97d79be55532dbab5, checked 2026-07-27

Measured configurations

No benchmark run passes the full metadata admission policy for this harness yet. Missing data is not scored as zero.

Benchmark policy and all runs
Context, not quality

Public ecosystem signals

Source-native observations for exact mapped artifacts and reviewed stable release trains. Different units and populations stay separate, and missing coverage is never treated as zero.

Compare all signals
  • GitHub stars15.63KFull-source repository; 1.18K forksOpen artifact

Routing, package retrievals, release downloads, editor installs, and repository interest observe different populations. They are never added together and never affect capability evidence, classification, or measured results.

Interpretation rulesSignals checked

First-party evidence

Each capability claim links to the first-party record that supports it.

25 first-party sourcesProduct record checked

Additional first-party sources

25 sources
View 24 more sources