indelible-mcp 5.2.0 → 5.2.1

package/CLI_HANDBOOK.md

@@ -1,5 +1,21 @@
 # Indelible CLI Handbook
 
+## Two Pilots (5.2.0)
+
+Indelible works with Claude Code, with OpenAI's Codex CLI, or with both at once on the same memory.
+
+- **Claude Code:** `claude mcp add indelible -- indelible-mcp`
+- **Codex CLI:** add to `~/.codex/config.toml` and restart Codex:
+
+  ```toml
+  [mcp_servers.indelible]
+  command = "indelible-mcp"
+  ```
+
+Every save is stamped with its author inside the encrypted record (`Saved by Claude` / `Saved by Codex` in the Context tab on indelible.one). Each pilot can only save its own conversations — a Codex call binds to its own rollout file, a Claude call binds to its own transcript, and a save with no valid binding refuses instead of guessing. The wallet admits one writer at a time, so concurrent pilots take turns instead of colliding; a busy wallet answers with a retryable message, not a double-spend.
+
+> Name check: the Diary companion below is also named "Codex" by default — that is a chat companion, not the OpenAI coding agent. The author stamps only ever come from the coding hosts.
+
 Standalone command-line interface for Indelible blockchain memory. Same wallet, same blockchain, same functions as the MCP server — but runnable directly.
 
 ---

package/CUSTOMER_AGENT_HANDBOOK.md

@@ -191,6 +191,14 @@ This fetches the pack and backfills meaning-vectors for your existing history. I
 
 **`diary_recall`** is the same power scoped to your companion's own history. `scope: "diary"` for saved diary entries, `"duo"` for live Claude-plus-companion rounds, `"all"` for both.
 
+### Two pilots on one memory (5.2.0)
+
+Your memory is not tied to one AI. Wire OpenAI's Codex CLI to the same install (`~/.codex/config.toml` → `[mcp_servers.indelible]` `command = "indelible-mcp"`) and it reads and writes the same chain as Claude Code. Every save is stamped with its author inside the encrypted record; the Context tab on indelible.one shows `Saved by Claude` or `Saved by Codex` once your record decrypts, and if an index ever claims a different author than your decrypted record proves, the app shows you both values and trusts neither.
+
+The pilots stay out of each other's way by construction. Each one can only save the conversation file it is actually bound to — its own transcript or its own rollout — and the wallet admits one writer at a time, so simultaneous saves take turns instead of double-spending. What one saves, the other can find: ask either pilot to `recall_context` and it reads work the other did, from its own seat, in its own time.
+
+(The Diary companion's default name is also "Codex" — that is the chat companion in section 5b, not the OpenAI coding agent. Author stamps only ever come from the coding hosts.)
+
 ---
 
 ## 5. Your first adversarial habit

package/LICENSE

@@ -11,7 +11,7 @@ Additional Use Grant: You may make use of the Licensed Work for personal,
                       commercial blockchain storage, session saving, or
                       encrypted vault service without written permission
                       from the Licensor.
-Change Date:          April 30, 2030
+Change Date:          August 7, 2030
 Change License:       MIT License
 
 Terms

package/README.md

@@ -1,6 +1,8 @@
 # Indelible MCP Server
 
-Blockchain-backed memory for Claude Code. Save your AI conversations permanently on BSV via a federated mesh of SPV bridges.
+Blockchain-backed memory for Claude Code **and OpenAI's Codex CLI**. Save your AI conversations permanently on BSV via a federated mesh of SPV bridges.
+
+**New in 5.2.0 — two pilots, one memory, signed work.** Run Claude, run Codex, or run both on the same on-chain memory. Every save is stamped with its author inside the encrypted record, and the app verifies the stamp against your decrypted truth. Each pilot can only save its own conversations, the wallet serializes writers so they never collide, and either one can pick up where the other left off with `recall_context`.
 
 > **New here?** Two guides ship with this package: **CUSTOMER_AGENT_HANDBOOK.md** (your agents on day one — the Witness, the Scribe, what runs for you) and **CLI_HANDBOOK.md** (every command + common errors). They are in the package install folder, or on indelible.one/docs.
 
@@ -40,6 +42,19 @@ Run `indelible-mcp --show-config` to get your config, or add this to your Claude
 }
 ```
 
+### 3b. Or wire OpenAI's Codex CLI — instead of Claude, or alongside it
+
+Add to `~/.codex/config.toml`, then restart Codex (the CLI and the VS Code extension share this config):
+
+```toml
+[mcp_servers.indelible]
+command = "indelible-mcp"
+```
+
+Codex's saves are stamped `Saved by Codex`; Claude's are stamped `Saved by Claude`. Both write to the same wallet and the same permanent memory — ask either one to "save this session" or "recall what we were working on."
+
+> Name check: the free Diary companion's default name is also "Codex" — that is a chat companion inside Indelible. This section is about OpenAI's Codex coding agent. Different lanes.
+
 ## Usage
 
 Once configured, just talk to Claude Code naturally:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "indelible-mcp",
-  "version": "5.2.0",
+  "version": "5.2.1",
   "description": "Blockchain-backed memory and code storage for Claude Code. Save AI conversations and source code permanently on BSV.",
   "type": "module",
   "main": "src/index.js",

package/src/index.js

@@ -11299,7 +11299,7 @@ Commands:
 }
 function printHelp() {
   console.log(`
-Indelible MCP \u2014 Blockchain memory for Claude Code (v5.2.0)
+Indelible MCP \u2014 Blockchain memory for Claude Code (v5.2.1)
 
 Setup:
   indelible-mcp setup --wif=KEY --pin=PIN    Import and encrypt your private key
@@ -11606,7 +11606,7 @@ function readStdin() {
 }
 var SERVER_INFO = {
   name: "indelible",
-  version: "5.2.0",
+  version: "5.2.1",
   description: "Blockchain-backed memory and code storage for Claude Code"
 };
 var TOOLS = [