Skip to content

docs: align sidecar ecosystem positioning #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
pramodbn27 merged 2 commits into from
Aug 15, 2026
Merged

docs: align sidecar ecosystem positioning #4

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9c2c7f1
docs: align sidecar ecosystem positioning
pramodbn27 Aug 15, 2026
ad2652f
docs: use portable org profile references
pramodbn27 Aug 15, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 8 additions & 1 deletion AGENTS.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,9 @@ alongside an autonomous agent runtime and evaluates whether the next action is
still aligned with user intent, policy, risk tolerance, and escalation rules
before the action is allowed to proceed.

At the ecosystem-role level, the preferred keyword is **SUPERVISE**. In
practice, the package covers both supervision and governance.

### Owns

- Decision Gate behavior, policy/risk evaluation, and intent-preservation
Expand Down Expand Up @@ -167,6 +170,9 @@ Full architecture and build order: [ROADMAP.md](ROADMAP.md).
`examples/`.
- When a roadmap item or milestone meaningfully changes status, update
`README.md` and `ROADMAP.md` in the same change.
- If that milestone or release changes the public ecosystem story, also update
the shared org-profile docs in the `.github` repository:
`profile/README.md` and, when relevant, `profile/ROADMAP.md`.
- When work is packaged as a release-ready change, also update
`pyproject.toml`, `src/agentic_sidecar/__init__.py`, and `CHANGELOG.md`.

Expand All @@ -178,7 +184,8 @@ Run `make check` before every push. It runs: lint → format-check → typecheck

1. Bump version in `pyproject.toml`, `src/agentic_sidecar/__init__.py`, and `CHANGELOG.md`
2. Commit: `git commit -am "release: vX.Y.Z"`
3. Tag: `git tag vX.Y.Z`
3. Tag: create an annotated `vX.Y.Z` tag and use the latest `CHANGELOG.md`
release section as the tag description
4. Push: `git push origin main --tags`

The `release-pypi.yml` workflow triggers on the tag push and publishes to
Expand Down
1 change: 1 addition & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -392,6 +392,7 @@ even though nothing consumes it across process boundaries yet.
| [AgenticLens](https://github.com/DeepAgentLabs/agenticlens) | What did the agent do, and what happened? |
| [Agentic Chaos](https://github.com/DeepAgentLabs/agentic-chaos) | How does the agent behave when things go wrong? |
| [Agentic MCP](https://github.com/DeepAgentLabs/mcp-server) | How does the agent interact with tools and external capabilities? |
| [AgenticOps Control Tower](https://github.com/DeepAgentLabs/agenticops-control-tower) | What is deployed, what governance posture exists across agents, and how do operators manage it centrally? |
Comment thread
pramodbn27 marked this conversation as resolved.
| **Agentic Sidecar** | Should the agent continue with this decision, and is it still acting according to intent? |

Each project is independently installable; none requires another as a hard
Expand Down
6 changes: 6 additions & 0 deletions ROADMAP.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -163,6 +163,12 @@ optional integration surface only, never a coordinated release).
Validate in: MCP tool calls are a natural decision boundary
([`concept.md` §28](concept.md)). A useful end-to-end check once
v0.1's Decision Gate exists is gating a real MCP tool call through it.
- `agenticops-control-tower`
Coordinate with: Control Tower is the future operator-facing layer above the
ecosystem. Once Sidecar emits stable runtime status and decision artifacts,
Control Tower should be able to summarize governance posture, intervention
counts, and escalation state centrally without taking ownership of the
Sidecar runtime.

For roadmap planning, treat ecosystem links as:

Expand Down