oacp-cli 0.2.3__tar.gz → 0.3.1__tar.gz

{oacp_cli-0.2.3 → oacp_cli-0.3.1}/CHANGELOG.md

@@ -5,6 +5,27 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [Unreleased]
+
+## [0.3.1] - 2026-05-12
+
+### Added
+
+- `auto_review` autonomy mode — an opt-in receiver-side autonomy profile that classifies inbound messages into auto-accept, pause, or hard-stop bands using clean / ambiguous / hard-stop trigger predicates. Configured via `receiver_config.autonomy_mode: auto_review` with `auto_review_profile` selecting `standard` or `tight`. Off by default; existing receivers continue to behave as `always_pause` unless they opt in. Ships with a conformance fixture suite under `tests/conformance/autonomy/` covering clean tasks, ambiguous scope, hard-stop triggers, and malformed config handling.
+
+### Changed
+
+- README: refreshed with a hero image and three screenshots illustrating inbox flow, doctor output, and the multi-agent workspace layout. Hub README copy, install path, and command table aligned with the current CLI surface.
+- Docs: link to companion oacp-skills repo from the README and onboarding pages so readers can find the skill library that pairs with the protocol.
+
+## [0.3.0] - 2026-04-29
+
+### Added
+
+- `oacp memory init|clone|pull|push|disable` subcommands for opt-in cross-machine sync of `$OACP_HOME/org-memory/**` and `$OACP_HOME/projects/*/memory/**` via a plain git repo rooted at `$OACP_HOME`. Three-state activation model: Disabled (no marker), Local-only (`init` without `--remote`), and Synced (`init --remote <url>` or `clone <url>`).
+- `oacp doctor --memory` advisory checks (10 checks covering marker presence, allowlist coverage, remote configuration, fetch/divergence state, and signing setup).
+- `oacp setup claude` now installs memory pull/push hook scripts and registers them in `.claude/settings.json` for Claude SessionStart and SessionEnd lifecycle events. Hooks are marker-gated and no-op silently unless `$OACP_HOME/.oacp-memory-repo` is present, so existing workflows are unaffected on machines that have not opted in.
+
 ## [0.2.3] - 2026-04-26
 
 ### Changed
@@ -121,6 +142,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Checkout step in github-release workflow job (#19)
 - Pre-release audit fixes: SHA-pinned actions, dangling doc refs (#15, #16)
 
+[0.3.1]: https://github.com/kiloloop/oacp/compare/v0.3.0...v0.3.1
+[0.3.0]: https://github.com/kiloloop/oacp/compare/v0.2.3...v0.3.0
 [0.2.3]: https://github.com/kiloloop/oacp/compare/v0.2.2...v0.2.3
 [0.2.2]: https://github.com/kiloloop/oacp/compare/v0.2.1...v0.2.2
 [0.2.1]: https://github.com/kiloloop/oacp/compare/v0.2.0...v0.2.1

{oacp_cli-0.2.3 → oacp_cli-0.3.1}/CONTRIBUTING.md

@@ -73,6 +73,7 @@ make preflight ARGS="--full"
 - Packet naming follows `<YYYYMMDD>_<topic>_<owner>_r<round>`.
 - Scripts use `python3` and avoid external dependencies beyond the standard library (exception: `pyyaml`).
 - Shell scripts use POSIX-compatible constructs where possible; bash-specific features require bash 3.2+.
+- README images should stay under ~500KB each. Use `docs/img/` for all README assets.
 
 ## Commit Messages
 

{oacp_cli-0.2.3 → oacp_cli-0.3.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: oacp-cli
-Version: 0.2.3
+Version: 0.3.1
 Summary: Open Agent Coordination Protocol CLI for file-based multi-agent workflows
 Project-URL: Homepage, https://github.com/kiloloop/oacp
 Project-URL: Repository, https://github.com/kiloloop/oacp
@@ -24,7 +24,7 @@ Requires-Python: >=3.9
 Requires-Dist: pyyaml>=6.0
 Description-Content-Type: text/markdown
 
-# OACP — Open Agent Coordination Protocol
+# OACP
 
 [![PyPI](https://img.shields.io/pypi/v/oacp-cli)](https://pypi.org/project/oacp-cli/)
 [![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)
@@ -32,11 +32,92 @@ Description-Content-Type: text/markdown
 [![Codex](https://img.shields.io/badge/Runtime-Codex-74AA9C.svg)](https://openai.com/index/codex/)
 [![PRs Welcome](https://img.shields.io/badge/PRs-Welcome-brightgreen)](https://github.com/kiloloop/oacp/pulls)
 
-> **[Try the quickstart →](examples/quickstart/)** — send your first message to an AI agent in 5 minutes.
+> Coordinate agents *without* the chaos.
 
-**Coordinate agents without the chaos.**
+A file-based protocol for multi-agent AI workflows. Two pillars — cross-agent communication and persistent shared memory. Across runtimes, projects, and machines. No daemons. No central server. Just files.
 
-A file-based protocol for multi-agent engineering workflows. OACP defines the message formats, review processes, and safety rules that let AI agents on different runtimes collaborate through a shared filesystem. Not a framework or SDK — just conventions, YAML schemas, and scripts that any runtime can implement.
+[Read the spec →](SPEC.md)
+
+```bash
+$ pip install oacp-cli
+```
+
+## See it in action
+
+<p align="center">
+  <img src="docs/img/oacp-cli-demo.png" alt="oacp send + watch terminal demo" width="584" />
+</p>
+
+The CLI ships structured tasks between agents and lets you watch the conversation in real time.
+
+## Live agent fleet
+
+<p align="center">
+  <img src="docs/img/oacp-fleet-thread.png" alt="claude / codex / gemini fleet with PR #42 review thread" width="650" />
+</p>
+
+Every multi-agent thread is a sequence of typed messages — `review_request`, `review_feedback`, `review_addressed`, `review_lgtm` — with explicit quality gates.
+
+<details>
+<summary>Text version (terminal browsing / grep / a11y)</summary>
+
+```
+PROJECT · my-app                                   ● live
+
+  C  claude   code           drafting PR #42
+  X  codex    cli            reviewing
+  G  gemini   api            idle
+
+  claude  →  review_request    "auth refactor"      [codex]
+  codex   →  review_feedback   2 minor, 0 blocking  [claude]
+  claude  →  review_addressed                       [codex]
+  codex   →  review_lgtm                            [merge]
+
+  thread #42 · 4 msgs · 8m                  quality gate ✓
+```
+
+</details>
+
+## Filesystem as protocol
+
+<p align="center">
+  <img src="docs/img/oacp-filesystem-tree.png" alt="$OACP_HOME directory tree with inbox/outbox/memory/artifacts" width="526" />
+</p>
+
+Everything is plain files in `$OACP_HOME`. Agents have `inbox/`, `outbox/`, `dead_letter/`. Projects have shared `memory/` (durable) and per-thread `artifacts/`, `checkpoints/`, `packets/`. Org-wide knowledge lives in `$OACP_HOME/org-memory/`.
+
+<details>
+<summary>Text version (terminal browsing / grep / a11y)</summary>
+
+```
+$OACP_HOME/projects/my-app/                  ● writing
+
+  agents/
+    claude/
+      inbox/         3 msgs           [in]
+      outbox/        12 sent          [out]
+      dead_letter/   empty            [dl]
+    codex/
+      inbox/         +1 new           [in]
+
+  memory/                             shared durable
+    project_facts.md     2.4 kb       [md]
+    decision_log.md      edited 3s ago [md]
+    open_threads.md      1.1 kb       [md]
+    known_debt.md        812 b        [md]
+
+  artifacts/                          build · research
+  checkpoints/                        progress
+  packets/                            review findings
+  workspace.json                      metadata        [json]
+
+$OACP_HOME/org-memory/                org-wide
+  recent.md            auto-loaded    [⌘]
+  rules.md             12 rules       [⌘]
+  decisions.md         org decisions  [⌘]
+```
+
+</details>
 
 ## Quick Start
 
@@ -47,7 +128,7 @@ oacp send my-project --from alice --to bob --type task_request \
   --subject "Implement feature X" --body "Details here..."
 ```
 
-When running inside a configured agent runtime, `--from` can be omitted — OACP infers the sender from `OACP_AGENT`, `AGENT_NAME`, or the agent card. See [QUICKSTART.md](QUICKSTART.md) for a full walkthrough.
+When running inside a configured agent runtime, `--from` can be omitted — OACP infers the sender from `OACP_AGENT`, `AGENT_NAME`, or the agent card. See [QUICKSTART.md](QUICKSTART.md) for a full walkthrough. Or try the [5-minute quickstart →](examples/quickstart/) to send your first message to a real AI agent.
 
 ### What you get
 
@@ -67,6 +148,18 @@ After installing, run `oacp doctor` to verify your environment is wired up:
 oacp doctor
 ```
 
+## Agent Skills
+
+OACP has companion agent skills that teach Claude, Codex, and other
+runtimes how to use the CLI and protocol in real workflows.
+
+Install or browse them here:
+
+- https://github.com/kiloloop/oacp-skills
+
+The core `oacp-cli` package remains the protocol/tooling kernel,
+while `oacp-skills` contains runtime guidance and workflows.
+
 ## Why OACP?
 
 When multiple AI agents work on the same codebase, they need a way to:
@@ -152,7 +245,7 @@ uv tool install .
 | `oacp send` | Send a protocol-compliant inbox message (`--from` auto-inferred) |
 | `oacp inbox` | List pending messages across agents (table or `--json`) |
 | `oacp watch` | Emit inbox delta events for one agent across selected projects |
-| `oacp memory` | Archive or restore project memory files |
+| `oacp memory` | Archive, restore, or git-sync project/org memory files |
 | `oacp agent` | Manage global agent profiles (`init`, `show`, `list`) |
 | `oacp org-memory` | Initialize org-level memory at `$OACP_HOME/org-memory/` |
 | `oacp write-event` | Write an event to `org-memory/events/` |
@@ -167,9 +260,9 @@ uv tool install .
 
 **`oacp watch`**: `--agent`, repeatable `--project`, `--all-projects`, `--json`, `--since` (default `now`), `--show-archived`
 
-**`oacp doctor`**: `--fix` (auto-fix safe issues), `--json`, `-o/--output`
+**`oacp doctor`**: `--fix` (auto-fix safe issues), `--memory`, `--json`, `-o/--output`
 
-**`oacp memory`**: `oacp memory archive <project> <file>`, `oacp memory restore <project> <file>`
+**`oacp memory`**: `init [--remote URL]`, `clone <URL> [--force]`, `pull`, `push`, `disable`, `archive <project> <file>`, `restore <project> <file>`
 
 </details>
 
@@ -182,7 +275,7 @@ If `OACP_HOME` is unset, workspace commands default to `~/oacp`.
 | **Inbox/Outbox** | Async messaging between agents via YAML files in `agents/<name>/inbox/` |
 | **Review Loop** | Structured code review: `review_request` → `review_feedback` → `review_addressed` → `review_lgtm` |
 | **Quality Gate** | Merge-readiness criteria: no unresolved P0/P1 findings, deferred nits tracked |
-| **Durable Memory** | Shared `memory/` directory with an active working set plus `memory/archive/` for historical memory |
+| **Durable Memory** | Shared `memory/` directory with an active working set plus `memory/archive/` for historical memory; optional `$OACP_HOME` git sync tracks only `org-memory/**` and `projects/*/memory/**` |
 | **Dispatch States** | Task lifecycle: `received` → `accepted` → `working` → `pr_opened` → `in_review` → `done` |
 | **Safety Defaults** | Baseline rules all agents follow: no force push, no secrets in commits, stage hygiene |
 

{oacp_cli-0.2.3 → oacp_cli-0.3.1}/README.md

@@ -1,4 +1,4 @@
-# OACP — Open Agent Coordination Protocol
+# OACP
 
 [![PyPI](https://img.shields.io/pypi/v/oacp-cli)](https://pypi.org/project/oacp-cli/)
 [![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)
@@ -6,11 +6,92 @@
 [![Codex](https://img.shields.io/badge/Runtime-Codex-74AA9C.svg)](https://openai.com/index/codex/)
 [![PRs Welcome](https://img.shields.io/badge/PRs-Welcome-brightgreen)](https://github.com/kiloloop/oacp/pulls)
 
-> **[Try the quickstart →](examples/quickstart/)** — send your first message to an AI agent in 5 minutes.
+> Coordinate agents *without* the chaos.
 
-**Coordinate agents without the chaos.**
+A file-based protocol for multi-agent AI workflows. Two pillars — cross-agent communication and persistent shared memory. Across runtimes, projects, and machines. No daemons. No central server. Just files.
 
-A file-based protocol for multi-agent engineering workflows. OACP defines the message formats, review processes, and safety rules that let AI agents on different runtimes collaborate through a shared filesystem. Not a framework or SDK — just conventions, YAML schemas, and scripts that any runtime can implement.
+[Read the spec →](SPEC.md)
+
+```bash
+$ pip install oacp-cli
+```
+
+## See it in action
+
+<p align="center">
+  <img src="docs/img/oacp-cli-demo.png" alt="oacp send + watch terminal demo" width="584" />
+</p>
+
+The CLI ships structured tasks between agents and lets you watch the conversation in real time.
+
+## Live agent fleet
+
+<p align="center">
+  <img src="docs/img/oacp-fleet-thread.png" alt="claude / codex / gemini fleet with PR #42 review thread" width="650" />
+</p>
+
+Every multi-agent thread is a sequence of typed messages — `review_request`, `review_feedback`, `review_addressed`, `review_lgtm` — with explicit quality gates.
+
+<details>
+<summary>Text version (terminal browsing / grep / a11y)</summary>
+
+```
+PROJECT · my-app                                   ● live
+
+  C  claude   code           drafting PR #42
+  X  codex    cli            reviewing
+  G  gemini   api            idle
+
+  claude  →  review_request    "auth refactor"      [codex]
+  codex   →  review_feedback   2 minor, 0 blocking  [claude]
+  claude  →  review_addressed                       [codex]
+  codex   →  review_lgtm                            [merge]
+
+  thread #42 · 4 msgs · 8m                  quality gate ✓
+```
+
+</details>
+
+## Filesystem as protocol
+
+<p align="center">
+  <img src="docs/img/oacp-filesystem-tree.png" alt="$OACP_HOME directory tree with inbox/outbox/memory/artifacts" width="526" />
+</p>
+
+Everything is plain files in `$OACP_HOME`. Agents have `inbox/`, `outbox/`, `dead_letter/`. Projects have shared `memory/` (durable) and per-thread `artifacts/`, `checkpoints/`, `packets/`. Org-wide knowledge lives in `$OACP_HOME/org-memory/`.
+
+<details>
+<summary>Text version (terminal browsing / grep / a11y)</summary>
+
+```
+$OACP_HOME/projects/my-app/                  ● writing
+
+  agents/
+    claude/
+      inbox/         3 msgs           [in]
+      outbox/        12 sent          [out]
+      dead_letter/   empty            [dl]
+    codex/
+      inbox/         +1 new           [in]
+
+  memory/                             shared durable
+    project_facts.md     2.4 kb       [md]
+    decision_log.md      edited 3s ago [md]
+    open_threads.md      1.1 kb       [md]
+    known_debt.md        812 b        [md]
+
+  artifacts/                          build · research
+  checkpoints/                        progress
+  packets/                            review findings
+  workspace.json                      metadata        [json]
+
+$OACP_HOME/org-memory/                org-wide
+  recent.md            auto-loaded    [⌘]
+  rules.md             12 rules       [⌘]
+  decisions.md         org decisions  [⌘]
+```
+
+</details>
 
 ## Quick Start
 
@@ -21,7 +102,7 @@ oacp send my-project --from alice --to bob --type task_request \
   --subject "Implement feature X" --body "Details here..."
 ```
 
-When running inside a configured agent runtime, `--from` can be omitted — OACP infers the sender from `OACP_AGENT`, `AGENT_NAME`, or the agent card. See [QUICKSTART.md](QUICKSTART.md) for a full walkthrough.
+When running inside a configured agent runtime, `--from` can be omitted — OACP infers the sender from `OACP_AGENT`, `AGENT_NAME`, or the agent card. See [QUICKSTART.md](QUICKSTART.md) for a full walkthrough. Or try the [5-minute quickstart →](examples/quickstart/) to send your first message to a real AI agent.
 
 ### What you get
 
@@ -41,6 +122,18 @@ After installing, run `oacp doctor` to verify your environment is wired up:
 oacp doctor
 ```
 
+## Agent Skills
+
+OACP has companion agent skills that teach Claude, Codex, and other
+runtimes how to use the CLI and protocol in real workflows.
+
+Install or browse them here:
+
+- https://github.com/kiloloop/oacp-skills
+
+The core `oacp-cli` package remains the protocol/tooling kernel,
+while `oacp-skills` contains runtime guidance and workflows.
+
 ## Why OACP?
 
 When multiple AI agents work on the same codebase, they need a way to:
@@ -126,7 +219,7 @@ uv tool install .
 | `oacp send` | Send a protocol-compliant inbox message (`--from` auto-inferred) |
 | `oacp inbox` | List pending messages across agents (table or `--json`) |
 | `oacp watch` | Emit inbox delta events for one agent across selected projects |
-| `oacp memory` | Archive or restore project memory files |
+| `oacp memory` | Archive, restore, or git-sync project/org memory files |
 | `oacp agent` | Manage global agent profiles (`init`, `show`, `list`) |
 | `oacp org-memory` | Initialize org-level memory at `$OACP_HOME/org-memory/` |
 | `oacp write-event` | Write an event to `org-memory/events/` |
@@ -141,9 +234,9 @@ uv tool install .
 
 **`oacp watch`**: `--agent`, repeatable `--project`, `--all-projects`, `--json`, `--since` (default `now`), `--show-archived`
 
-**`oacp doctor`**: `--fix` (auto-fix safe issues), `--json`, `-o/--output`
+**`oacp doctor`**: `--fix` (auto-fix safe issues), `--memory`, `--json`, `-o/--output`
 
-**`oacp memory`**: `oacp memory archive <project> <file>`, `oacp memory restore <project> <file>`
+**`oacp memory`**: `init [--remote URL]`, `clone <URL> [--force]`, `pull`, `push`, `disable`, `archive <project> <file>`, `restore <project> <file>`
 
 </details>
 
@@ -156,7 +249,7 @@ If `OACP_HOME` is unset, workspace commands default to `~/oacp`.
 | **Inbox/Outbox** | Async messaging between agents via YAML files in `agents/<name>/inbox/` |
 | **Review Loop** | Structured code review: `review_request` → `review_feedback` → `review_addressed` → `review_lgtm` |
 | **Quality Gate** | Merge-readiness criteria: no unresolved P0/P1 findings, deferred nits tracked |
-| **Durable Memory** | Shared `memory/` directory with an active working set plus `memory/archive/` for historical memory |
+| **Durable Memory** | Shared `memory/` directory with an active working set plus `memory/archive/` for historical memory; optional `$OACP_HOME` git sync tracks only `org-memory/**` and `projects/*/memory/**` |
 | **Dispatch States** | Task lifecycle: `received` → `accepted` → `working` → `pr_opened` → `in_review` → `done` |
 | **Safety Defaults** | Baseline rules all agents follow: no force push, no secrets in commits, stage hygiene |
 

{oacp_cli-0.2.3 → oacp_cli-0.3.1}/SPEC.md

@@ -16,7 +16,7 @@ OACP is not a framework or SDK. It is a set of conventions, YAML schemas, and sh
 3. [Review Loop Protocol](#3-review-loop-protocol)
 4. [Cross-Runtime Sync](#4-cross-runtime-sync)
 5. [Agent Safety Defaults](#5-agent-safety-defaults)
-6. [Org-Level Memory](#6-org-level-memory)
+6. [Org-Level Memory and Sync](#6-org-level-memory-and-sync)
 7. [Kernel Script Inventory](#7-kernel-script-inventory)
 
 ---
@@ -79,7 +79,12 @@ Messages are YAML files. Filename convention: `<timestamp>_<from>_<type>.yaml`
 | `subject` | string | Subject line |
 | `body` | string | Message content (multi-line markdown) |
 
-**Optional fields:** `expires_at`, `channel`, `related_packet`, `related_pr`, `conversation_id`, `parent_message_id`, `context_keys`
+**Optional fields:** `expires_at`, `channel`, `autonomy_hint`, `related_packet`, `related_pr`, `conversation_id`, `parent_message_id`, `context_keys`
+
+`autonomy_hint` is an advisory sender hint, such as `auto_proceed`. Receivers
+remain authoritative: local autonomy config, message content, safety defaults,
+and runtime/tool permissions determine whether a message can be accepted without
+interactive human confirmation.
 
 ### Message Types
 
@@ -164,7 +169,7 @@ received → accepted → working → pr_opened → in_review → done
 
 ### Key Transitions
 
-- **`received` → `accepted`**: Agent reads and accepts the task. Ack recommended for P0/P1.
+- **`received` → `accepted`**: Agent reads and accepts the task. Ack recommended for P0/P1. When accepted by autonomy policy, this transition is preserved and records `accepted_by`, `human_confirmed`, `autonomy_mode`, `policy_ref`, `policy_hash`, and `reason_codes`.
 - **`working` → `pr_opened`**: Agent opens a PR. **Notification required** with `WIP:` subject prefix.
 - **`pr_opened` → `in_review`**: Agent requests cross-agent review via `review_request`.
 - **`in_review` → `done`**: PR merged after review approval. Guard: `pr_merged AND review_approved`.
@@ -202,6 +207,23 @@ The dispatcher (e.g., an orchestrator agent) tracks dispatches from its perspect
 - **Non-PR tasks**: done = deliverable provided or question answered
 - Final notification must include `merge_sha` (PR tasks) or `results_summary` (non-PR tasks)
 
+### Acceptance Metadata
+
+Receivers must not collapse `received → accepted`, even when a task is
+auto-accepted. Transition metadata records who or what accepted the task:
+
+```yaml
+transition: received_to_accepted
+accepted_by: autonomy_policy   # human | autonomy_policy | --autonomous-flag
+human_confirmed: false
+autonomy_mode: auto_review
+policy_ref: agents/codex/config.yaml
+policy_hash: sha256:...
+reason_codes:
+  - task_profile_present
+  - risk_threshold_passed
+```
+
 ### Brainstorm Lifecycle
 
 Brainstorm messages follow a simpler lifecycle: `received` → `researching` → `report_delivered`. No PR, no review loop. The dispatcher sees: `Sent` → `In progress` → `Responded`.
@@ -402,6 +424,27 @@ Credential scoping: [`docs/protocol/credential_scoping.md`](docs/protocol/creden
 
 These defaults apply to all agents (Claude, Codex, Gemini) unless a project-level config explicitly overrides a specific rule. Safety defaults can only be made **stricter** by project rules, never relaxed.
 
+Autonomy introduces a separate receiver acceptance policy layer; it does not
+relax the safety floor. OACP distinguishes three layers:
+
+1. **Safety defaults** — non-negotiable baseline constraints, such as no
+   unapproved push/deploy/merge/publish, no destructive commands, no secrets,
+   and disciplined staging. Projects may make these stricter, never looser.
+2. **Receiver acceptance policy** — configurable rules for whether a receiver
+   may move a message from `received` to `accepted` without interactive human
+   confirmation. This is governed by `agents/<receiver>/config.yaml` and
+   [`docs/protocol/autonomy.md`](docs/protocol/autonomy.md).
+3. **Runtime/tool safety** — runtime-specific permission gates that still apply
+   after acceptance, such as editor edit approval, shell sandboxing, or Codex
+   approval modes. OACP acceptance never grants runtime tool permissions.
+
+Regardless of autonomy mode, receivers must pause on any of: destructive command
+tokens (`rm -rf`, `--force`, `--no-verify`,
+`--dangerously-skip-permissions`), external side effects
+(push/deploy/merge/publish/rotate/install), or modifications to auth, config,
+secrets, dependencies, public repos, pricing/commercial content, or memory SSOT,
+unless explicitly authorized by a separate safety-default exception.
+
 #### Git Safety
 
 - No push/deploy without explicit approval from the user or dispatcher
@@ -451,7 +494,7 @@ Agents operate under least-privilege credentials:
 
 ---
 
-## 6. Org-Level Memory
+## 6. Org-Level Memory and Sync
 
 Full specification: [`docs/protocol/org_memory.md`](docs/protocol/org_memory.md)
 
@@ -459,6 +502,16 @@ Full specification: [`docs/protocol/org_memory.md`](docs/protocol/org_memory.md)
 
 Shared, cross-project memory for multi-agent organizations. Agents across projects read org-wide decisions, conventions, and events from a single location. Complements per-project memory — does not replace it.
 
+OACP can optionally sync curated memory across machines using one plain git
+repository rooted at `$OACP_HOME`. This feature is opt-in and tracks only:
+
+- `$OACP_HOME/org-memory/**`
+- `$OACP_HOME/projects/<project>/memory/**`
+
+Cross-machine inbox delivery, `agents/` runtime state, `status.yaml`, concurrent
+writer protocols, encrypted transport, and runtime-specific memory outside
+`$OACP_HOME` are out of scope.
+
 ### Directory Structure
 
 ```
@@ -470,6 +523,28 @@ $OACP_HOME/org-memory/
     └── YYYYMMDD-HHMMSS-short-slug.md
 ```
 
+When memory sync is enabled, `$OACP_HOME` also contains:
+
+```text
+$OACP_HOME/
+├── .gitignore            # positive allowlist
+├── .oacp-memory-repo     # tracked marker; activates hooks
+├── org-memory/           # tracked
+└── projects/*/memory/    # tracked
+```
+
+Canonical root `.gitignore`:
+
+```gitignore
+*
+!*/
+!.gitignore
+!.oacp-memory-repo
+!org-memory/**
+!projects/*/memory/**
+projects/*/memory/.cache/
+```
+
 ### Key Concepts
 
 - **`recent.md`** is the always-loaded cross-project context. Agents read it at session start via session-init hooks. Kept concise (~150 lines) as a rolling summary of current state, not full history.
@@ -506,11 +581,37 @@ Agents write events only (append-only). The coordinator curates topical files an
 
 - **`oacp org-memory init`** — scaffold `$OACP_HOME/org-memory/` with default files
 - **`oacp write-event`** — create an event file with proper frontmatter
+- **`oacp memory init [--remote URL]`** — initialize the `$OACP_HOME` memory git repo, marker, canonical allowlist, optional remote, and initial commit
+- **`oacp memory clone <URL> [--force]`** — clone a memory repo into `$OACP_HOME`; refuses non-empty targets unless `--force` moves the existing directory aside
+- **`oacp memory pull`** — advisory fetch plus fast-forward-only pull; warns loudly on dirty, ahead, behind, diverged, or fetch-failed states and never auto-merges
+- **`oacp memory push`** — stages only the memory allowlist, commits as `memory: <agent>@<host> <date> (N files)`, then pushes when a remote is configured
+- **`oacp memory disable`** — removes `.oacp-memory-repo` locally while leaving `.git/` intact
+- **`oacp doctor --memory`** — runs advisory memory sync checks for marker state, allowlist drift, tracked/untracked leakage, clean/ahead/behind/diverged state, remote reachability, commit staleness, `agents/` leakage, and per-project memory overlay safety
 
 ### Integration with Session Init
 
 Agents can read `org-memory/recent.md` at session start for cross-project context. This integration is runtime-specific — for example, Claude Code loads it via a session-init hook, while other runtimes may read it explicitly. Topical files and `events/` are available for on-demand reading when agents need deeper org context.
 
+Memory sync has three activation states:
+
+| State | Trigger | Behavior |
+|-------|---------|----------|
+| Disabled | No `.oacp-memory-repo` marker | Hooks no-op silently; `oacp doctor --memory` reports not configured |
+| Local-only | `oacp memory init` | Wrap-up commits memory locally for audit history; no push |
+| Synced | `oacp memory init --remote URL` or `oacp memory clone <URL>` | Session start pulls fast-forward updates; wrap-up commits and pushes |
+
+Lifecycle hooks must check for `$OACP_HOME/.oacp-memory-repo` first and exit
+without output when it is absent. Claude runtime setup installs hook scripts for
+`SessionStart` pull and wrap-up/session-end push:
+
+1. Session start runs `oacp memory pull`. It exits advisory-successfully, pulls
+   only clean behind states with `--ff-only`, and warns loudly when memory is
+   dirty, ahead, diverged, behind, or remote fetch fails.
+2. Wrap-up runs `oacp memory push`. It stages only `.gitignore`,
+   `.oacp-memory-repo`, `org-memory/**`, and `projects/*/memory/**`; commits
+   with the fixed terse message format; pushes when a remote exists; and warns
+   loudly when memory is dirty, behind, diverged, or push fails.
+
 ---
 
 ## 7. Kernel Script Inventory
@@ -532,7 +633,8 @@ Scripts marked **CLI** are exposed as `oacp` subcommands. Scripts marked **scrip
 | `agent_profile.py` | Two-tier agent profile management | CLI: `oacp agent` |
 | `send_inbox_message.py` | Compose and send inbox messages | CLI: `oacp send` |
 | `oacp_inbox.py` | List pending inbox messages | CLI: `oacp inbox` |
-| `memory_cli.py` | Archive or restore project memory files | CLI: `oacp memory` |
+| `memory_cli.py` | Archive, restore, or git-sync project/org memory files | CLI: `oacp memory` |
+| `memory_sync.py` | Shared git allowlist and memory sync helpers | imported by CLI/doctor |
 | `setup_runtime.py` | Generate runtime-specific config files | CLI: `oacp setup` |
 | `init_org_memory.py` | Scaffold org-level memory directory | CLI: `oacp org-memory` |
 | `write_event.py` | Write timestamped events to org-memory | CLI: `oacp write-event` |
@@ -618,6 +720,7 @@ scripts/init_packet.sh <project> <packet_id>  # (no CLI wrapper yet)
 | Shared workspace | [`docs/protocol/multi_agent_shared_workspace.md`](docs/protocol/multi_agent_shared_workspace.md) |
 | Cross-runtime sync | [`docs/protocol/cross_runtime_sync.md`](docs/protocol/cross_runtime_sync.md) |
 | Session init | [`docs/protocol/session_init.md`](docs/protocol/session_init.md) |
+| Receiver autonomy | [`docs/protocol/autonomy.md`](docs/protocol/autonomy.md) |
 | Safety defaults | [`docs/protocol/agent_safety_defaults.md`](docs/protocol/agent_safety_defaults.md) |
 | Credential scoping | [`docs/protocol/credential_scoping.md`](docs/protocol/credential_scoping.md) |
 | Runtime capabilities | [`docs/protocol/runtime_capabilities.md`](docs/protocol/runtime_capabilities.md) |

{oacp_cli-0.2.3 → oacp_cli-0.3.1}/docs/guides/runtime_capability_matrix.md

@@ -1,10 +1,10 @@
 # Cross-Runtime Parity Matrix
 
-**Date**: 2026-04-24
+**Date**: 2026-04-29
 
 This is a capability comparison across 3 agent runtimes (Claude Code, Codex, Gemini), compiled from each runtime's self-report and current runtime changelogs. Use this as a reference when deciding which agent to assign for a given task.
 
-Claude was last checked against Claude Code `v2.1.118`.
+Claude was last checked against Claude Code `v2.1.123`.
 
 Codex was last checked against app update `26.415`, CLI `0.123.0`, and OpenAI's GPT-5.5 launch note from 2026-04-23.
 

{oacp_cli-0.2.3 → oacp_cli-0.3.1}/docs/protocol/agent_safety_defaults.md

@@ -30,6 +30,21 @@ Follow `credential_scoping.md` in this directory for:
 - Per-agent credential boundaries
 - Rotation and revocation procedures
 
+## Autonomy Hard Stops
+
+Receiver autonomy controls only whether a message can move from `received` to
+`accepted` without interactive human confirmation. It does not relax this safety
+floor.
+
+Regardless of autonomy mode, receivers must pause on any of:
+
+- Destructive command tokens: `rm -rf`, `--force`, `--no-verify`, `--dangerously-skip-permissions`
+- External side effects: push, deploy, merge, publish, credential rotation, dependency install
+- Sensitive scope: auth, config, secrets, dependencies, public repos, pricing/commercial content, memory SSOT
+
+The only exception is an explicit, separate safety-default exception. The
+Phase 1 autonomy RFC does not introduce any such exception.
+
 ## Scope Discipline
 
 - **Do not edit files outside the requested scope** — if a task says "fix X in file Y", do not refactor file Z.