switchboard-local 0.1.0__tar.gz

switchboard_local-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Vinay Gupta
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

switchboard_local-0.1.0/PKG-INFO

@@ -0,0 +1,270 @@
+Metadata-Version: 2.4
+Name: switchboard-local
+Version: 0.1.0
+Summary: Privacy-aware, local-first router across CLI coding agents (Codex, Claude Code) and local LLMs (Ollama).
+Author-email: Vinay Gupta <ai.vinaygupta@gmail.com>
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/aivinay/switchboard
+Project-URL: Repository, https://github.com/aivinay/switchboard
+Project-URL: Issues, https://github.com/aivinay/switchboard/issues
+Keywords: llm,llm-routing,local-first,privacy,ollama,claude-code,codex,ai-agents,orchestration,on-device
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: fastapi>=0.115.0
+Requires-Dist: httpx>=0.27.0
+Requires-Dist: pydantic>=2.8.0
+Requires-Dist: pydantic-settings>=2.4.0
+Requires-Dist: pyyaml>=6.0.2
+Requires-Dist: sqlmodel>=0.0.22
+Requires-Dist: uvicorn[standard]>=0.30.0
+Provides-Extra: dev
+Requires-Dist: mypy>=1.11.0; extra == "dev"
+Requires-Dist: pytest>=8.3.0; extra == "dev"
+Requires-Dist: ruff>=0.6.0; extra == "dev"
+Provides-Extra: finance
+Requires-Dist: yfinance>=0.2.50; extra == "finance"
+Provides-Extra: router
+Requires-Dist: numpy>=1.26; extra == "router"
+Dynamic: license-file
+
+<h1 align="center">Switchboard</h1>
+
+<p align="center"><strong>A privacy-aware, local-first router across your CLI coding agents and local LLMs.</strong></p>
+
+<p align="center">
+  <a href="https://github.com/aivinay/switchboard/actions/workflows/ci.yml"><img src="https://github.com/aivinay/switchboard/actions/workflows/ci.yml/badge.svg" alt="CI"></a>
+  <a href="RELEASE.md"><img src="https://img.shields.io/badge/PyPI-pending-lightgrey.svg" alt="PyPI: pending"></a>
+  <img src="https://img.shields.io/badge/python-3.11%2B-blue.svg" alt="Python 3.11+">
+  <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-green.svg" alt="License: MIT"></a>
+  <a href="https://doi.org/10.5281/zenodo.20789935"><img src="https://img.shields.io/badge/DOI-10.5281%2Fzenodo.20789935-blue.svg" alt="DOI"></a>
+</p>
+
+<p align="center">
+  <a href="#get-started-60-seconds">Install</a> ·
+  <a href="#how-it-works">How it works</a> ·
+  <a href="#context-memory-and-tokens">Context</a> ·
+  <a href="#proof">Proof</a> ·
+  <a href="#privacy">Privacy</a> ·
+  <a href="#the-paper">Paper</a> ·
+  <a href="docs/">Docs</a>
+</p>
+
+---
+
+> Switchboard routes prompts to the right model while preserving context through
+> local semantic memory and context compression, keeping sensitive work local,
+> and reducing unnecessary premium-model usage.
+
+It's built for the single-workstation setup where the scarce resources aren't
+dollars-per-token but **subscription quota**, **privacy**, and a pile of
+**heterogeneous agent interfaces**.
+
+## What it does
+
+- **Routes** across local [Ollama](https://ollama.com) models, the **Codex** CLI, and **Claude Code** — deterministic rules first, with optional tiny learned classifiers for recall.
+- **Private mode** — a deterministic keyword/PII/secret-format floor blocks sensitive prompts from ever reaching a subscription backend, even on fallback.
+- **Grounds** answers with deterministic tools (time/date, safe calculator, unit conversion, keyless live stock & news) instead of letting a model guess.
+- **Carries context** across backend switches: recent user, assistant, and tool turns are assembled into one redacted session prompt.
+- **Compresses** long context with a Headroom-inspired layer; the model-boundary pass only summarizes recent conversation, while trusted facts, retrieved memory, and the current request survive intact.
+- **Remembers** across backends via local embedding-based semantic memory, with SQLite search available for direct memory lookup.
+- **Explains every decision** and records metadata-only telemetry (no prompt/response bodies).
+- **Ships its own evaluation** — a 100-case quality benchmark, a local LLM-as-judge, and a multi-run statistical harness.
+
+## How it works
+
+```
+  UI / CLI  ──►  Session manager (shared history across all backends)
+                      │
+                      ▼
+              Capability detector (regex) ◄──► deterministic tools
+                      │  (learned tool dispatcher recovers misses; tool verifies)
+                      ▼
+              Privacy floor  (keywords + PII + secret formats — a match is FINAL)
+                      │  (learned sensitivity escalator may only ADD protection)
+                      ▼
+              Deterministic policy   ← always wins; unknown ⇒ local
+                      │  (learned router supplies recall: tool / local / coding / reasoning)
+                      ▼
+              Context builder + redaction ◄── semantic memory
+                      │
+                      ▼
+              Compression (metadata + history-only context pass)
+                      │
+                      ▼
+        Ollama (default) │ Codex (coding) │ Claude Code (reasoning)
+                      │
+                      ▼
+              Response sanitizer ─► metadata-only telemetry
+```
+
+The organizing invariant: **deterministic policy always precedes and overrides
+the learned components.** Privacy, tool grounding, forced selection, and
+fallback keep working even when the local model runtime — and therefore every
+learned component — is down.
+
+## Get started (60 seconds)
+
+PyPI release is pending. Until the first release is published:
+
+```bash
+pip install "git+https://github.com/aivinay/switchboard.git"
+```
+
+After the PyPI release:
+
+```bash
+pip install switchboard-local
+```
+
+```bash
+# point it at a local model runtime (install Ollama, then pull a small model)
+ollama pull llama3.2:3b
+
+# sanity-check your setup
+switchboard doctor
+
+# ask — Switchboard routes it, grounds it, and tells you why
+switchboard ask "summarize this error log and suggest a fix"
+
+# see the routing decision without running anything
+switchboard route "refactor the auth module and add tests"
+
+# prefer your browser? launch the local web UI, then open http://127.0.0.1:8080/ui
+switchboard ui
+```
+
+Requires **Python 3.11+**. Codex / Claude Code backends are optional — without
+them, everything routes locally. See [docs/usage.md](docs/usage.md).
+
+## Context, memory, and tokens
+
+Switchboard has two user-facing CLI surfaces:
+
+- `switchboard route ...` and bare `switchboard ask ...` use the personal local-first route/call workflow.
+- The web UI and `switchboard ask --backend auto ...` use the stateful core workflow: shared sessions, model switching, semantic-memory retrieval, context-boundary compression, and backend telemetry all run on the same path.
+
+Example stateful CLI session:
+
+```bash
+switchboard ask --backend auto --new-session "Remember: prefer local models for private notes."
+switchboard ask --backend auto --session <session_id> --memory "What should you remember?"
+```
+
+Long prompts and long sessions record token estimates and savings metadata. The request-level pass can shorten an oversized raw prompt; the context-boundary pass then compresses only `<recent_conversation>`. The `<trusted_facts>`, `<long_term_memory>`, and `<current_user_request>` blocks are protected from that second pass so grounding and intent are not traded away for token budget.
+
+Memory is local. `switchboard memory add` stores the item in SQLite and, when `semantic_memory_enabled` is on and Ollama can serve `nomic-embed-text`, indexes an embedding for cross-backend retrieval. `switchboard memory search` works as local text search even when embeddings are unavailable.
+
+Details: [docs/context-memory-compression.md](docs/context-memory-compression.md).
+
+## Proof
+
+A 100-case benchmark across five task categories (coding, reasoning,
+summarization, private, grounding), run on real backends and judged by a local
+model, over **multiple independent runs** (means shown; full per-condition
+numbers, confidence intervals, and significance tests are in the paper):
+
+| Policy            | Quality (1–5) | Premium usage | Privacy leaks | Answered |
+|-------------------|:-------------:|:-------------:|:-------------:|:--------:|
+| always-local      | 3.4           | 0%            | **0**         | 100%     |
+| rules             | 3.8           | 27%           | **0**         | 100%     |
+| hybrid            | 3.9           | 28%           | **0**         | 100%     |
+| **learned**       | **4.1**       | 38%           | **0**         | 100%     |
+| always-premium    | 4.6           | 100%          | **0**         | 61%¹     |
+
+<sub>¹ The "just use the premium agent for everything" baseline must <em>block</em> every
+sensitive prompt to stay leak-free, so its coverage collapses — exactly the gap
+Switchboard closes. <strong>Zero measured leaks in every condition and every run.</strong></sub>
+
+These numbers come from a real-backend benchmark whose full harness travels with the paper's [reproduction bundle on Zenodo](https://doi.org/10.5281/zenodo.20789935).
+
+## Privacy
+
+Switchboard is local-first and privacy-aware by construction:
+
+- The **deterministic privacy floor runs before any non-local routing**; a positive verdict is final and cannot be overridden by a learned component or by prompt wording.
+- **Secret-format detection** (cloud keys, JWTs, PEM blocks, env credentials) shares its patterns with context redaction, so the routing boundary and the redactor can't drift apart.
+- **Metadata-only telemetry** — prompt and response bodies are not stored by default.
+- Semantic-memory **embeddings and the eval judge run locally**.
+
+Switchboard deliberately does **not** resell API access, scrape web UIs, or
+bypass provider limits — subscription CLIs are invoked exactly as the
+authenticated user could invoke them, in read-only sandbox modes. See
+[SECURITY.md](SECURITY.md) and [docs/privacy.md](docs/privacy.md).
+
+<details>
+<summary><b>What's inside</b></summary>
+
+- **Deterministic router** — keyword rules; unknown prompts default local-first.
+- **Learned router / tool dispatcher / sensitivity escalator** — tiny softmax classifiers over a locally-computed embedding (~50 ms, pure-Python inference), each retrainable in seconds from your own thumbs-down corrections behind golden-accuracy gates. They fail closed to the deterministic path.
+- **Tools** — time/date with timezones, safe abstract-syntax-tree calculator, unit conversion, keyless live stock quotes & news.
+- **Compression** — structure-aware, deterministic, dependency-free; preserves task header, code blocks, tracebacks, and grounded facts.
+- **Semantic memory** — `nomic-embed-text` embeddings, cosine retrieval, local memory commands, and SQLite text-search fallback for direct search.
+- **Evaluation** — mock evals (CI), real-backend smoke suite, 100-case quality benchmark, adversarial tester/developer dogfooding loop.
+
+</details>
+
+## Configuration
+
+Settings live in `config/personal.yaml` (ships with safe local-first defaults —
+see `config/personal.example.yaml`). Highlights:
+
+```yaml
+preferences:
+  router_mode: "learned"      # rules | llm | hybrid | learned
+  private_mode: true          # block sensitive prompts from non-local backends
+  allow_cloud: false
+  compression_enabled: true
+  compression_threshold_tokens: 1000
+  semantic_memory_enabled: true
+  semantic_memory_top_k: 3
+  finance_provider: "yahoo"
+  news_provider: "google_news_rss"
+```
+
+Provider API keys are referenced **by environment-variable name** (e.g.
+`OPENAI_API_KEY`), never inline. See [docs/overrides.md](docs/overrides.md).
+
+## The paper
+
+Switchboard is described in a preprint — *"Privacy-Aware Hybrid Routing Across
+Heterogeneous AI Agents on a Single Workstation."* The manuscript, the multi-run
+benchmark harness, the statistical-aggregation and figure scripts, and the
+per-case records are archived together as a reproduction bundle on Zenodo:
+[10.5281/zenodo.20789935](https://doi.org/10.5281/zenodo.20789935).
+
+This repository ships only the software. It deliberately does not carry the
+paper's experiment-running or figure-generation tooling — that lives with the
+archival record so the code stays focused on the router itself.
+
+## Development
+
+```bash
+make install     # .venv + editable install with dev extras
+make check       # ruff + mypy + the full test suite
+```
+
+See [CONTRIBUTING.md](CONTRIBUTING.md). Issues and PRs welcome — please preserve
+the privacy invariant described there.
+
+## Citing Switchboard
+
+A preprint is available on Zenodo with a citable DOI —
+[10.5281/zenodo.20789935](https://doi.org/10.5281/zenodo.20789935). See
+[CITATION.cff](CITATION.cff) for machine-readable metadata.
+
+> V. Gupta, "Switchboard: Privacy-Aware Hybrid Routing Across Heterogeneous AI
+> Agents on a Single Workstation," Zenodo, 2026, doi:10.5281/zenodo.20789935.
+
+## License
+
+[MIT](LICENSE) © 2026 Vinay Gupta

switchboard_local-0.1.0/README.md

@@ -0,0 +1,231 @@
+<h1 align="center">Switchboard</h1>
+
+<p align="center"><strong>A privacy-aware, local-first router across your CLI coding agents and local LLMs.</strong></p>
+
+<p align="center">
+  <a href="https://github.com/aivinay/switchboard/actions/workflows/ci.yml"><img src="https://github.com/aivinay/switchboard/actions/workflows/ci.yml/badge.svg" alt="CI"></a>
+  <a href="RELEASE.md"><img src="https://img.shields.io/badge/PyPI-pending-lightgrey.svg" alt="PyPI: pending"></a>
+  <img src="https://img.shields.io/badge/python-3.11%2B-blue.svg" alt="Python 3.11+">
+  <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-green.svg" alt="License: MIT"></a>
+  <a href="https://doi.org/10.5281/zenodo.20789935"><img src="https://img.shields.io/badge/DOI-10.5281%2Fzenodo.20789935-blue.svg" alt="DOI"></a>
+</p>
+
+<p align="center">
+  <a href="#get-started-60-seconds">Install</a> ·
+  <a href="#how-it-works">How it works</a> ·
+  <a href="#context-memory-and-tokens">Context</a> ·
+  <a href="#proof">Proof</a> ·
+  <a href="#privacy">Privacy</a> ·
+  <a href="#the-paper">Paper</a> ·
+  <a href="docs/">Docs</a>
+</p>
+
+---
+
+> Switchboard routes prompts to the right model while preserving context through
+> local semantic memory and context compression, keeping sensitive work local,
+> and reducing unnecessary premium-model usage.
+
+It's built for the single-workstation setup where the scarce resources aren't
+dollars-per-token but **subscription quota**, **privacy**, and a pile of
+**heterogeneous agent interfaces**.
+
+## What it does
+
+- **Routes** across local [Ollama](https://ollama.com) models, the **Codex** CLI, and **Claude Code** — deterministic rules first, with optional tiny learned classifiers for recall.
+- **Private mode** — a deterministic keyword/PII/secret-format floor blocks sensitive prompts from ever reaching a subscription backend, even on fallback.
+- **Grounds** answers with deterministic tools (time/date, safe calculator, unit conversion, keyless live stock & news) instead of letting a model guess.
+- **Carries context** across backend switches: recent user, assistant, and tool turns are assembled into one redacted session prompt.
+- **Compresses** long context with a Headroom-inspired layer; the model-boundary pass only summarizes recent conversation, while trusted facts, retrieved memory, and the current request survive intact.
+- **Remembers** across backends via local embedding-based semantic memory, with SQLite search available for direct memory lookup.
+- **Explains every decision** and records metadata-only telemetry (no prompt/response bodies).
+- **Ships its own evaluation** — a 100-case quality benchmark, a local LLM-as-judge, and a multi-run statistical harness.
+
+## How it works
+
+```
+  UI / CLI  ──►  Session manager (shared history across all backends)
+                      │
+                      ▼
+              Capability detector (regex) ◄──► deterministic tools
+                      │  (learned tool dispatcher recovers misses; tool verifies)
+                      ▼
+              Privacy floor  (keywords + PII + secret formats — a match is FINAL)
+                      │  (learned sensitivity escalator may only ADD protection)
+                      ▼
+              Deterministic policy   ← always wins; unknown ⇒ local
+                      │  (learned router supplies recall: tool / local / coding / reasoning)
+                      ▼
+              Context builder + redaction ◄── semantic memory
+                      │
+                      ▼
+              Compression (metadata + history-only context pass)
+                      │
+                      ▼
+        Ollama (default) │ Codex (coding) │ Claude Code (reasoning)
+                      │
+                      ▼
+              Response sanitizer ─► metadata-only telemetry
+```
+
+The organizing invariant: **deterministic policy always precedes and overrides
+the learned components.** Privacy, tool grounding, forced selection, and
+fallback keep working even when the local model runtime — and therefore every
+learned component — is down.
+
+## Get started (60 seconds)
+
+PyPI release is pending. Until the first release is published:
+
+```bash
+pip install "git+https://github.com/aivinay/switchboard.git"
+```
+
+After the PyPI release:
+
+```bash
+pip install switchboard-local
+```
+
+```bash
+# point it at a local model runtime (install Ollama, then pull a small model)
+ollama pull llama3.2:3b
+
+# sanity-check your setup
+switchboard doctor
+
+# ask — Switchboard routes it, grounds it, and tells you why
+switchboard ask "summarize this error log and suggest a fix"
+
+# see the routing decision without running anything
+switchboard route "refactor the auth module and add tests"
+
+# prefer your browser? launch the local web UI, then open http://127.0.0.1:8080/ui
+switchboard ui
+```
+
+Requires **Python 3.11+**. Codex / Claude Code backends are optional — without
+them, everything routes locally. See [docs/usage.md](docs/usage.md).
+
+## Context, memory, and tokens
+
+Switchboard has two user-facing CLI surfaces:
+
+- `switchboard route ...` and bare `switchboard ask ...` use the personal local-first route/call workflow.
+- The web UI and `switchboard ask --backend auto ...` use the stateful core workflow: shared sessions, model switching, semantic-memory retrieval, context-boundary compression, and backend telemetry all run on the same path.
+
+Example stateful CLI session:
+
+```bash
+switchboard ask --backend auto --new-session "Remember: prefer local models for private notes."
+switchboard ask --backend auto --session <session_id> --memory "What should you remember?"
+```
+
+Long prompts and long sessions record token estimates and savings metadata. The request-level pass can shorten an oversized raw prompt; the context-boundary pass then compresses only `<recent_conversation>`. The `<trusted_facts>`, `<long_term_memory>`, and `<current_user_request>` blocks are protected from that second pass so grounding and intent are not traded away for token budget.
+
+Memory is local. `switchboard memory add` stores the item in SQLite and, when `semantic_memory_enabled` is on and Ollama can serve `nomic-embed-text`, indexes an embedding for cross-backend retrieval. `switchboard memory search` works as local text search even when embeddings are unavailable.
+
+Details: [docs/context-memory-compression.md](docs/context-memory-compression.md).
+
+## Proof
+
+A 100-case benchmark across five task categories (coding, reasoning,
+summarization, private, grounding), run on real backends and judged by a local
+model, over **multiple independent runs** (means shown; full per-condition
+numbers, confidence intervals, and significance tests are in the paper):
+
+| Policy            | Quality (1–5) | Premium usage | Privacy leaks | Answered |
+|-------------------|:-------------:|:-------------:|:-------------:|:--------:|
+| always-local      | 3.4           | 0%            | **0**         | 100%     |
+| rules             | 3.8           | 27%           | **0**         | 100%     |
+| hybrid            | 3.9           | 28%           | **0**         | 100%     |
+| **learned**       | **4.1**       | 38%           | **0**         | 100%     |
+| always-premium    | 4.6           | 100%          | **0**         | 61%¹     |
+
+<sub>¹ The "just use the premium agent for everything" baseline must <em>block</em> every
+sensitive prompt to stay leak-free, so its coverage collapses — exactly the gap
+Switchboard closes. <strong>Zero measured leaks in every condition and every run.</strong></sub>
+
+These numbers come from a real-backend benchmark whose full harness travels with the paper's [reproduction bundle on Zenodo](https://doi.org/10.5281/zenodo.20789935).
+
+## Privacy
+
+Switchboard is local-first and privacy-aware by construction:
+
+- The **deterministic privacy floor runs before any non-local routing**; a positive verdict is final and cannot be overridden by a learned component or by prompt wording.
+- **Secret-format detection** (cloud keys, JWTs, PEM blocks, env credentials) shares its patterns with context redaction, so the routing boundary and the redactor can't drift apart.
+- **Metadata-only telemetry** — prompt and response bodies are not stored by default.
+- Semantic-memory **embeddings and the eval judge run locally**.
+
+Switchboard deliberately does **not** resell API access, scrape web UIs, or
+bypass provider limits — subscription CLIs are invoked exactly as the
+authenticated user could invoke them, in read-only sandbox modes. See
+[SECURITY.md](SECURITY.md) and [docs/privacy.md](docs/privacy.md).
+
+<details>
+<summary><b>What's inside</b></summary>
+
+- **Deterministic router** — keyword rules; unknown prompts default local-first.
+- **Learned router / tool dispatcher / sensitivity escalator** — tiny softmax classifiers over a locally-computed embedding (~50 ms, pure-Python inference), each retrainable in seconds from your own thumbs-down corrections behind golden-accuracy gates. They fail closed to the deterministic path.
+- **Tools** — time/date with timezones, safe abstract-syntax-tree calculator, unit conversion, keyless live stock quotes & news.
+- **Compression** — structure-aware, deterministic, dependency-free; preserves task header, code blocks, tracebacks, and grounded facts.
+- **Semantic memory** — `nomic-embed-text` embeddings, cosine retrieval, local memory commands, and SQLite text-search fallback for direct search.
+- **Evaluation** — mock evals (CI), real-backend smoke suite, 100-case quality benchmark, adversarial tester/developer dogfooding loop.
+
+</details>
+
+## Configuration
+
+Settings live in `config/personal.yaml` (ships with safe local-first defaults —
+see `config/personal.example.yaml`). Highlights:
+
+```yaml
+preferences:
+  router_mode: "learned"      # rules | llm | hybrid | learned
+  private_mode: true          # block sensitive prompts from non-local backends
+  allow_cloud: false
+  compression_enabled: true
+  compression_threshold_tokens: 1000
+  semantic_memory_enabled: true
+  semantic_memory_top_k: 3
+  finance_provider: "yahoo"
+  news_provider: "google_news_rss"
+```
+
+Provider API keys are referenced **by environment-variable name** (e.g.
+`OPENAI_API_KEY`), never inline. See [docs/overrides.md](docs/overrides.md).
+
+## The paper
+
+Switchboard is described in a preprint — *"Privacy-Aware Hybrid Routing Across
+Heterogeneous AI Agents on a Single Workstation."* The manuscript, the multi-run
+benchmark harness, the statistical-aggregation and figure scripts, and the
+per-case records are archived together as a reproduction bundle on Zenodo:
+[10.5281/zenodo.20789935](https://doi.org/10.5281/zenodo.20789935).
+
+This repository ships only the software. It deliberately does not carry the
+paper's experiment-running or figure-generation tooling — that lives with the
+archival record so the code stays focused on the router itself.
+
+## Development
+
+```bash
+make install     # .venv + editable install with dev extras
+make check       # ruff + mypy + the full test suite
+```
+
+See [CONTRIBUTING.md](CONTRIBUTING.md). Issues and PRs welcome — please preserve
+the privacy invariant described there.
+
+## Citing Switchboard
+
+A preprint is available on Zenodo with a citable DOI —
+[10.5281/zenodo.20789935](https://doi.org/10.5281/zenodo.20789935). See
+[CITATION.cff](CITATION.cff) for machine-readable metadata.
+
+> V. Gupta, "Switchboard: Privacy-Aware Hybrid Routing Across Heterogeneous AI
+> Agents on a Single Workstation," Zenodo, 2026, doi:10.5281/zenodo.20789935.
+
+## License
+
+[MIT](LICENSE) © 2026 Vinay Gupta

switchboard_local-0.1.0/pyproject.toml

@@ -0,0 +1,85 @@
+[project]
+name = "switchboard-local"
+version = "0.1.0"
+description = "Privacy-aware, local-first router across CLI coding agents (Codex, Claude Code) and local LLMs (Ollama)."
+readme = "README.md"
+requires-python = ">=3.11"
+license = "MIT"
+license-files = ["LICENSE"]
+authors = [{ name = "Vinay Gupta", email = "ai.vinaygupta@gmail.com" }]
+keywords = [
+    "llm", "llm-routing", "local-first", "privacy", "ollama",
+    "claude-code", "codex", "ai-agents", "orchestration", "on-device",
+]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Science/Research",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+]
+dependencies = [
+    "fastapi>=0.115.0",
+    "httpx>=0.27.0",
+    "pydantic>=2.8.0",
+    "pydantic-settings>=2.4.0",
+    "pyyaml>=6.0.2",
+    "sqlmodel>=0.0.22",
+    "uvicorn[standard]>=0.30.0",
+]
+
+[project.urls]
+Homepage = "https://github.com/aivinay/switchboard"
+Repository = "https://github.com/aivinay/switchboard"
+Issues = "https://github.com/aivinay/switchboard/issues"
+
+[project.scripts]
+switchboard = "switchboard.cli:main"
+ai-switchboard = "switchboard.cli:main"
+
+[build-system]
+requires = ["setuptools>=69", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools.packages.find]
+include = ["switchboard*"]
+
+[tool.setuptools.package-data]
+"switchboard.config" = ["*.yaml", "*.json"]
+
+[project.optional-dependencies]
+dev = [
+    "mypy>=1.11.0",
+    "pytest>=8.3.0",
+    "ruff>=0.6.0",
+]
+finance = [
+    "yfinance>=0.2.50",
+]
+router = [
+    "numpy>=1.26",
+]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+pythonpath = ["."]
+
+[tool.ruff]
+line-length = 100
+target-version = "py311"
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "UP", "B", "SIM"]
+
+[tool.mypy]
+python_version = "3.11"
+plugins = ["pydantic.mypy"]
+warn_unused_ignores = true
+warn_redundant_casts = true
+check_untyped_defs = true
+disallow_untyped_defs = false
+ignore_missing_imports = true

switchboard_local-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

switchboard_local-0.1.0/switchboard/__init__.py

@@ -0,0 +1,8 @@
+"""Switchboard package."""
+
+from importlib.metadata import PackageNotFoundError, version
+
+try:
+    __version__ = version("switchboard-local")
+except PackageNotFoundError:
+    __version__ = "0.1.0"

switchboard_local-0.1.0/switchboard/app/__init__.py

@@ -0,0 +1 @@
+"""FastAPI application package."""

switchboard_local-0.1.0/switchboard/app/api/__init__.py

@@ -0,0 +1 @@
+"""API routers."""