Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

English · 简体中文

ADS Agent Bridge

ADS Agent Bridge logo

From an exact ADS selection or blank circuit to checked data and an editable DDS result.

PyPI Python CI License

An RF engineer goes from a blank circuit through simulation to checked native results

Finish a circuit-to-results task in one conversation

“Start from a blank workspace, build this testbench, run the simulation, export the data, and leave the response plot editable in DDS.”

Built in ADS Result left editable in DDS
Native ADS schematic built in the public acceptance workspace Editable native ADS Data Display page created from the accepted dataset

The public ADS 2026 Update 2.1 acceptance completed the whole request:

  • built a six-instance AC circuit from an empty workspace;
  • ran the circuit simulation and returned 31 finite rows;
  • exported CSV and created a native DDS equation and rectangular plot;
  • saved, closed, and freshly reopened the editable result;
  • completed the four-stage Runtime plan in 4.469 seconds.

These are real ADS application-window captures; the DDS curve remains native and editable. The same maintained path can continue from an exact schematic, layout, library-tree, or DDS selection copied with Copy ADS Context, and can run an already-generated Momentum input on a protected sibling copy.

ADS Agent Bridge connects Codex or Pi Agent to the ADS installation and object you actually selected. Version-matched local documentation, the DE/DDS context plug-in, controlled live sessions, and bounded automation stay with ADS on the EDA host; repeated remote work reuses EDA Bridge Runtime instead of rebuilding an SSH command for every action.

Start in three steps

Prerequisites: a licensed ADS installation, Windows or Linux, and Python 3.10 or later for the public command.

pipx install ads-agent-bridge
ads-agent setup
ads-agent quickstart

Installing the package automatically installs its compatible eda-bridge-runtime Python dependency. You do not need to install a second Python package by hand. If the Agent runs on another computer, enable the EDA Bridge Runtime MCP/plugin there; the ADS-only host does not need the Agent-facing plugin.

setup discovers installed ADS versions, asks for an explicit selection, and installs the recoverable context add-on and two cooperating Skills. quickstart passes only after documentation query, add-on registration, disposable workspace creation, minimal circuit simulation, and dataset readback have each passed.

If pipx or a suitable Python is not yet available, use the versioned bootstrap for Linux or Windows PowerShell. The bootstrap creates an isolated environment and does not replace an externally managed system Python.

Then open an exact workspace:

ads-agent --pretty launch --workspace /path/to/MyWorkspace_wrk
ads-agent --pretty status
ads-agent disconnect

disconnect leaves ADS running. shutdown requests native exit only for a matching Agent-owned session.

What you can ask your Agent

Natural-language request What the Bridge checks
“Which ADS installations are here, and what can this one do?” Discovers multiple versions, keeps the choice explicit, and probes real capabilities.
“Find the correct API for this installed ADS version.” Searches a private, version-scoped local index and returns focused source evidence.
“Prove automation works before touching my project.” Creates a disposable workspace, runs a minimal AC simulation, and reads the dataset through separate gates.
“Use the schematic, layout, cell, folder, or DDS item I selected.” Resolves the copied ADS_CONTEXT instead of guessing the foreground window.
“Open this exact workspace and tell me what ADS is doing.” Verifies workspace, process, ADS version, display, ownership, visible UI, and blocking dialogs.
“Apply these schematic edits safely.” Modifies a non-overwriting copy and accepts it only after save, close, fresh reopen, and exact assertions.
“Simulate this circuit, give me the data, and build the DDS plots.” Generates the netlist, runs the circuit simulator, checks numeric dataset columns, exports CSV, and fresh-reopens the native DDS report.
“Run this already-generated Momentum input.” Preserves the source, solves a sibling copy, and checks a complete finite N-port result before promotion.
“Disconnect but keep ADS open.” Separates client disconnect from identity-checked native shutdown.

The capability matrix gives the maintained evidence and stop rule behind every row.

The selection plug-in

After ADS restarts, Copy ADS Context is available from supported DE schematic, layout, symbol, folder/library-tree, and DDS selections. The copied text identifies the software, host-local origin, workspace, object kind, selection, and freshness needed by the Agent. It contains no password, live port, or permission to mutate.

This is the normal user interaction:

  1. Select the intended object in ADS.
  2. Click Copy ADS Context.
  3. Paste it into the conversation and describe the task naturally.
  4. Review the target and evidence returned by the Agent.

See the context interaction contract for exact selection coverage.

Public evidence

The maintained acceptance path uses real ADS installations on Windows and Linux. It separately checks documentation, context capture, live session identity, safe dialog supervision, typed schematic construction, circuit simulation, dataset and CSV readback, native DDS equation and plot creation, and generated-input Momentum execution.

The maintained blank-workspace → schematic → simulation → native DDS path passed as one four-stage Runtime plan in 4.469 seconds, with 31 finite rows, a deterministic native dataset, CSV, and a freshly reopened DDS report. See the sanitized workflow evidence.

Two narrow ADS 2027 comparisons are also public:

  • In nine isolated knowledge tasks, Bridge completed 9/9, used 10.4% fewer total tokens, and had 5.2% higher median latency than the official ADS MCP. Method and data
  • In a three-run headless AC microbenchmark, both paths completed 3/3; Bridge used 43.4% fewer total tokens and had 21.5% lower median wall time. Method and data

These are small, isolated regression suites, not a universal product ranking. They do not compare installation, the DE/DDS plug-in, GUI session control, dialog handling, or every ADS solver workflow; this is not a full-product comparison. The sanitized headless per-run summary is also available as JSON.

Local and remote use follow one path

On a remote ADS host, repeated Agent operations use:

ads-agent runtime serve

EDA Bridge Runtime keeps one SSH stdio process alive, records the purpose and timing of each operation, and never exposes the embedded ADS Bridge port. If Agent and ADS share a machine, register the same service as a local connection; do not bypass Runtime. The engineering behavior and evidence remain the same in both topologies.

Safety and privacy

  • Local documentation, indexes, workspaces, tokens, and results stay on the EDA host unless the user deliberately exports them.
  • Live endpoints bind to loopback and require a random session token.
  • A reused session must match the selected ADS installation and exact workspace.
  • A Context identifies the target but never authorizes editing or simulation.
  • Structured edits protect the source and require fresh-reopen assertions.
  • Dialog actions require a fresh process/window fingerprint, not screen coordinates.
  • Shutdown refuses unverified or user-owned sessions and never force-kills ADS.
  • Arbitrary embedded Python and dynamic AEL remain disabled by default.

Support and boundaries

ADS generation Support level
ADS 2025 and later Stable target, decided by runtime capability probes
ADS 2024 Update 2 Preview
ADS 2023 Update 2 through ADS 2024 Update 1 Experimental
Older installations Documentation-only when local docs can be discovered

Next

  • richer RF testbenches and reusable parameterized cells;
  • native DDS markers, Smith charts, tables, and multi-page result workbooks;
  • layout construction and broader Momentum, RFPro, FEM, SIPro, and PIPro journeys.

More information

To remove only this ADS integration while preserving unrelated add-ons:

ads-agent addon uninstall

Metadata

Release files for ads-agent-bridge 0.1.0a40

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for ads-agent-bridge 0.1.0a40
File Size Uploaded
ads_agent_bridge-0.1.0a40.tar.gz 4.5 MB Details

Built distribution (wheel)

Table of built distributions (wheels) for ads-agent-bridge 0.1.0a40
File Interpreter ABI Platform
ads_agent_bridge-0.1.0a40-py3-none-any.whl Python 3 none any Details

Total release size: 4.7 MB

Release files / ads_agent_bridge-0.1.0a40.tar.gz

Download URL ads_agent_bridge-0.1.0a40.tar.gz
Size 4.5 MB
Tags Source
SHA-256 checksum
How to use checksums
a3fc5874fb05a10f20c9bb94c57f07ae4a240f1a2b907c5b7a4a0e4a77b4132a
BLAKE2b-256 checksum
How to use checksums
8f4a24cb3d6e250cc9631281714474389bd3d856496aaf135b66e10a6f519e96
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 30, 2026.

Transparency log

Release files / ads_agent_bridge-0.1.0a40-py3-none-any.whl

Download URL ads_agent_bridge-0.1.0a40-py3-none-any.whl
Size 119.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
0d659f7250bee9c537a017924695e9e1c848328cc98530db67832a0e2d28fd6c
BLAKE2b-256 checksum
How to use checksums
32c3a296fae128c5ce719038fa765b3f7b4e095177e0db96bbf0f5c1c260ff5a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 30, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

0.1.0a40 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page