Spine — governed, provenance-grounded autonomous delivery

Spine

Governed, provenance-grounded autonomous delivery — turn requirements into reviewed, tested pull requests, with a human in control.

Naming. Spine is the product. It's distributed as the synaptixs-spine package and its command is orchestrator — those names stay in install lines and commands throughout the docs.

Spine reads a requirement (from Confluence, Notion, a Markdown file, or an OpenSpec spec-driven change), understands your target repo, generates code grounded in that repo's own conventions, writes and runs tests, and opens a pull request for you to review. It pauses for your approval before it starts and before anything merges. Nothing is pushed, merged, or written to your tracker unless you say so.

It's built for teams who want agents that are inspectable, reproducible, and safe to run on real code — not demos.

pip install synaptixs-spine
orchestrator init && orchestrator doctor                  # scaffold .env, check readiness
orchestrator sdlc feature --source file://./spec.md --safe   # build locally — no pushes, no PRs

Documentation

Guide Read it for
Setup & Install Installing the CLI, the .env, and standing up the full stack (Temporal + Postgres) for the autonomous pipeline.
User Guide A step-by-step walkthrough: from your first local build to a real PR, local models, the web dashboard, and connecting tools (MCP).
Using Spine from Codex Drive Spine from the Codex app — install (plugin or MCP server), credentials, the tool reference, and end-to-end greenfield + brownfield walkthroughs.
Using Spine from Claude Code Drive Spine from Claude Code — install (plugin or MCP server), credentials, the tool reference, and end-to-end greenfield + brownfield walkthroughs.
Features & Capabilities The capability catalog — everything Spine can do today, its status, the command/flag to use it, and a link to each deep dive.
Knowledge Graph (PKG) How Spine understands your codebase — the code-native graph, its model, the CLI, and how it powers brownfield and greenfield work.
Operations & Developer Guide How to operate it: deployment modes, the full environment-variable reference, and standing up each advanced capability — including the semantic spine (ontomesh × infodrift).
Community brief A one-page overview to share — what it does, lifecycle coverage, how to try it, and the feedback we're looking for.

New here? Install → User Guide Steps 1–4. That's the whole everyday workflow in about ten minutes.

Features & capabilities

Requirements → reviewed PR. Point it at a requirements source and a code repo. It extracts a backlog of intents, writes a spec, generates the implementation and tests, gets them green, and opens a PR — with two human gates (before building, before merging). A safe mode builds entirely locally (branch + diff, no external writes) so you can inspect everything first.

Code-grounded understanding. Before generating, it builds a Product Knowledge Graph of your repo — modules, types, functions, call sites, blast radius — and grounds new code in what already exists, so output reads like your team wrote it. Works across Python, Java, TypeScript, C#, C, and C++, plus SQL data-layer comprehension (schema, queries, stored procedures, migration folding). orchestrator understand writes a committed, code-true memory-bank/ your whole team (and any AI tool) can read.

Governed autonomy. The workflow itself is a typed, validated artifact. A planner decomposes the objective, a runtime executes it, and per-edge verifiers check every step against schemas, evidence, and policy. Failures trigger replan, a human approval, or a clean stop. Every tool call, approval, and decision lands in an append-only audit log, and each run is capped by a spend budget.

Learns across runs. Cross-run semantic memory lets the agent recall conventions, pitfalls, and decisions from past runs — each memory cites the run it came from.

You can see inside it. Live OpenTelemetry tracing covers every LLM call, loop step, and tool call, joined to the audit log — so you can debug a run, not just read its result.

Use it your way. A CLI for scripting and CI, a web dashboard (delegate runs, watch them live, approve gates inline), a terminal UI, and MCP in both directions — consume external MCP tools, or expose the whole pipeline as an MCP server to Claude Code, Codex, or your IDE.

Bring your own model. Multi-provider via LiteLLM (Anthropic, OpenAI, Bedrock), or run fully offline on a local model (Ollama). Mix models per stage.

Durable. Long-running pipelines are checkpointed (Temporal + Postgres) — they survive restarts and resume across human approval pauses.

How it works

  requirement (Confluence / Notion / Markdown)
        │
        ▼
   plan ──► validate ──► generate code ──► run tests ──► review ──► open PR
        │        (grounded in your repo's knowledge graph)        │
        └──────────── per-edge verifiers + audit ────────────────┘
                 human gate 1 ▲                    ▲ human gate 2
                 (before build)                    (before merge)
Concept What it is
Planner → GraphIR Turns an objective into a typed, validated execution graph (nodes, edges, budgets, approval points).
Registry Versioned agent templates + tool contracts the planner assembles from.
Runtime LangGraph-based executor with Postgres checkpointing and typed state.
Verifier chain Per-edge schema / confidence / evidence / policy checks that gate every handoff.
Approval gates First-class nodes that pause for human review and resume on your decision.
Audit log Append-only record of every tool call, approval, and policy decision.

FAQ

Does it merge code on its own? No. It opens a PR; a human reviews and merges. There are two approval gates — before building and before merging — and safe mode makes no external writes at all.

Where does my code/data go? To whichever LLM provider you configure — or nowhere external, if you run a local model (Ollama). Generated code stays in a local branch until you choose --live.

Do I need Docker or a database? Not for the everyday path (sdlc feature --safe builds one requirement locally). The autonomous multi-feature pipeline + web dashboard needs Temporal + Postgres — see the Setup guide.

Which languages and models? Code generation and comprehension cover Python, Java, TypeScript, C#, C, and C++ (C# also extracts ASP.NET Core endpoints and EF Core entities; C builds the #include graph and merges header declarations with their source definitions; C++ is a superset of the C front-end that adds classes, namespaces, inheritance, member functions, and templates, and shares C's CMake/Meson + ctest codegen). SQL ([sql] extra) adds data-layer comprehension — schema, foreign keys, views, queries, stored procedures, and ordered-migration folding, grounded from .sql source — plus greenfield codegen (sdlc feature --language sql): it generates a migration and validates it by applying it to an ephemeral database (in-memory SQLite by default). Any LiteLLM-supported provider (Anthropic, OpenAI, Bedrock) or a local Ollama model; you can set a different model per stage.

How is it safe to run on real repos? Write guards on generated files, allow-listed + write-gated external tools, a per-run spend budget, an append-only audit trail, and human approval before any push or merge.

CLI or web UI? Either — they drive the same engine and the same API. Use the CLI for scripting/CI, the web UI (or terminal UI) for watching runs and approving gates by hand.

Can other tools call it? Yes. It speaks MCP both ways: it can use external MCP servers, and it can run as an MCP server so Claude Code / Codex / your IDE can call the pipeline (with the same gates).

Contributing & feedback

We'd love your input. Pick the channel that fits:

  • 🐛 Bug? Open a bug report.
  • 💡 Feature idea / enhancement? Open a feature request.
  • 💬 Question, feedback, or idea to discuss? Start a Discussion.
  • 🔒 Security issue? Please follow SECURITY.md — don't open a public issue.

See CONTRIBUTING.md and the CODE_OF_CONDUCT.md for how contributions are reviewed.

License

MIT License. See LICENSE.

Project links

Data verified by PyPI on Jul 14, 2026
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Newer release available (3.32.0)

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for steven-synaptixs from gravatar.com steven-synaptixs

Credits

Author: Synaptixs

GitHub Statistics

Data verified by PyPI on Jul 14, 2026
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

License

MIT License (MIT)

Requires

Python >=3.12

Provides Extra

c cpp csharp dev java mcp otel sdlc security sql sql-postgres tui typescript

Tags

agents codegen llm orchestration sdlc temporal

Classifiers

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

synaptixs_spine-3.2.0.tar.gz (1.3 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

synaptixs_spine-3.2.0-py3-none-any.whl (674.9 kB view details)

Uploaded Python 3

File details

Details for the file synaptixs_spine-3.2.0.tar.gz.

File metadata

  • Download URL: synaptixs_spine-3.2.0.tar.gz
  • Upload date:
  • Size: 1.3 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for synaptixs_spine-3.2.0.tar.gz
Algorithm Hash digest
SHA256 1fc87f2b1a6c738ed446914f3464277e57885f2835de7c14255837cb2693144d
MD5 f497587b682ba00250ab63ab8f70c372
BLAKE2b-256 63e6d8a2972aee9ae4ad3d95007e245059cfdd56fc90db7ec1049eb9120bd4c9

See more details on using hashes here.

Provenance

The following attestation bundles were made for synaptixs_spine-3.2.0.tar.gz:

Publisher: publish-pypi.yml on synaptixs/spine

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file synaptixs_spine-3.2.0-py3-none-any.whl.

File metadata

  • Download URL: synaptixs_spine-3.2.0-py3-none-any.whl
  • Upload date:
  • Size: 674.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for synaptixs_spine-3.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 09aa83be4b2f69912d4b55fd2378bcce18aa424bc54bb034b6ed635cfbfb3eaf
MD5 c28253451e1db72d9049f579a9a82e7b
BLAKE2b-256 32cf4a6660dbb1dee5f97f3119ec49ddfbc663a03c931413c77978a399b17972

See more details on using hashes here.

Provenance

The following attestation bundles were made for synaptixs_spine-3.2.0-py3-none-any.whl:

Publisher: publish-pypi.yml on synaptixs/spine

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

3.32.0

2 files

3.31.0

2 files

3.30.0

2 files

3.29.1

2 files

3.29.0

2 files

3.28.0

2 files

3.27.0

2 files

3.26.1

2 files

3.26.0

2 files

3.25.1

2 files

3.25.0

2 files

3.24.0

2 files

3.23.0

2 files

3.22.0

2 files

3.21.0

2 files

3.20.0

2 files

3.19.0

2 files

3.18.1

2 files

3.18.0

2 files

3.17.0

2 files

3.16.2

2 files

3.16.1

2 files

3.16.0

2 files

3.15.0

2 files

3.14.0

2 files

3.13.0

2 files

3.12.0

2 files

3.11.1

2 files

3.10.0

2 files

3.9.3

2 files

3.9.1

2 files

3.9.0

2 files

3.8.4

2 files

3.8.3

2 files

3.8.2

2 files

3.8.1

2 files

3.8.0

2 files

3.7.0

2 files

3.6.1

2 files

3.6.0

2 files

3.5.0

2 files

3.4.0

2 files

3.3.0

2 files

This release

3.2.0 This release

2 files

3.1.0

2 files

3.0.0

2 files

2.8.1

2 files

2.8.0

2 files

2.7.0

2 files

2.6.2

2 files

2.6.1

2 files

2.6.0

2 files

2.5.0

2 files

2.4.0

2 files

2.3.0

2 files

2.2.0

2 files

2.0.1

2 files

1.24.0

2 files

1.23.0

2 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