Coding agent

Ante

Alpha terminal harness with goal loops, local models, persistent memory, and subagents.

Status
Active
License
Apache-2.0 components; preview binary terms
Evidence
Documented, 17 sources
Product record checked
2026-08-02

At a glance

An alpha terminal coding harness distributed as a self-contained binary, with repository and shell tools, explicit goal loops, automatic context compaction, persistent project memory, delegated subagents, local GGUF inference, MCP, skills, headless runs, and a structured server protocol. Local execution is host-first: permissions and tool filters govern calls but do not establish an operating-system sandbox.

Good choice if

  • Terminal workflows that need provider switching, subscription login, or fully local GGUF inference
  • Longer repository tasks using explicit goal conditions, automatic compaction, persistent memory, and delegated subagents
  • Scripted or editor-integrated operation through headless JSON events or the long-lived JSONL and WebSocket protocol

Check before choosing

  • Ante is an alpha research preview with documented breaking-change and incomplete-functionality risk; binary distribution may change or stop during the preview period
  • The public repository exposes documentation, protocol and SDK components, a process-execution component, and evaluation adapters, but the core harness remains private and ships as a prebuilt binary
  • Local tools execute with host privileges and no documented operating-system sandbox; interactive approvals and permission rules are controls over calls rather than process isolation
See 3 more considerations
  • Headless runs always imply yolo approval, and MCP tools require no approval by default, so unattended use needs restrictive tool filters and an independently constrained runtime
  • Goal completion and the optional verification pass are product-internal model judgments rather than independent proof of task success; iteration caps and external time or spend limits remain necessary
  • Persistent memory can influence later sessions, while session resume restores conversation state rather than rolling back files, shell effects, network actions, or external services

Capability support

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

External tools (MCP)
DocumentedProduct-supported MCP integrationSource · checked 2026-08-02The source establishes the mechanism, not its quality or availability in every mode.
Reusable skills
DocumentedProduct-supported reusable skill packagesSource · checked 2026-08-02Support does not establish portability, package quality, safety, or adoption.
Local models
DocumentedLocal or self-hosted model pathSource · checked 2026-08-02The source establishes the mechanism, not its quality or availability in every mode.
Agent parallelism
DocumentedDelegated or parallel agent workflowSource · checked 2026-08-02The source establishes the mechanism, not its quality or availability in every mode.
Runs without an open UI
DocumentedNon-interactive or automation surfaceSource · checked 2026-08-02The source establishes the mechanism, not its quality or availability in every mode.
Browser control
OptionalOptional Chromium control in Ante builds compiled with the browser featureSource · checked 2026-08-02Browser availability depends on the distributed build and still follows the host execution and approval boundary.
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
Not documentedNo first-class support established by the current recordAbsence of current documentation is not proof that the capability is impossible.

Getting started

Install the Ante binary, connect a supported API or subscription provider or select a local GGUF model, review permission and tool-filter rules, and add external isolation before unattended mutation.

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.

  • Repository tool execution

    Documented

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

  • Task-aware context management

    Documented

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

  • Model-independent runtime control

    Documented

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

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 & integrationsExtensible + browserDocumented mechanism, not a performance score.
  • Context & statePersistent stateDocumented mechanism, not a performance score.
  • Lifecycle & recoverySession resumeDocumented mechanism, not a performance score.
  • ObservabilityStructured tracesDocumented mechanism, not a performance score.
  • VerificationTool-assistedDocumented mechanism, not a performance score.
  • Governance & permissionsPolicy controlsDocumented 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

Unrankedsupport-only repository
Security policy
Not found
CI workflow
Present at inspected commit
Automated tests
Present at inspected commit
Evaluation assets
Present at inspected commit
Contributor documentation
Not found

The 127-file public alpha tree exposes documentation, protocol and SDK components, one process-execution test module, two workflows, and project-owned Harbor and benchmark assets. The official README states that the core harness remains private and ships as a prebuilt binary, so this repository cannot establish code-verifiable core capability. Vendor evaluation assets are not independent benchmark evidence, and no product score is imported.

Inspect commit 8ce59518ed8a2ddda46c07cbb0b6fb1f528438a3, checked 2026-08-02

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.

View this harness in Usage
  • Latest stable releasev0.preview.68Released 2026-08-01; 43 stable releases in 90 daysOpen release
  • OpenRouter 30d tokens13.6B#40 coding app; 2026-07-03 to 2026-08-01Open app page
  • Release asset downloads28562 stable releases; 248 matched assetsOpen artifact
  • GitHub stars583Support repository; 8 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.

17 first-party sourcesProduct record checked

Product and interfaces

3 sources
View 2 more sources

Execution and control

3 sources
View 2 more sources

Agents, state and recovery

4 sources
View 3 more sources

Automation and extensions

4 sources
View 3 more sources

Releases and public code audit

3 sources
View 2 more sources

Ecosystem context

OpenRouter CLI agent directory Discovery and usage context only; Ante membership and capabilities are established from first-party documentation and the pinned official repository. Observed 2026-08-02.