clawdi 0.8.0 → 0.8.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -73,7 +73,7 @@ Clawdi is the shared layer underneath:
73
73
 
74
74
  - **Cross-agent memory** — Store durable preferences, decisions, facts, and project context once. Search them from any connected agent.
75
75
  - **Portable skills** — Upload or install agent instructions once, then sync them into every registered agent.
76
- - **Project sharing** — Share read-only Project access, accept it from the CLI inbox, and explicitly attach accepted Projects to Agents when they should be used at runtime.
76
+ - **Project sharing** — Share read-only Project access from the dashboard or CLI, accept it from a share page or CLI inbox, and explicitly attach accepted Projects to Agents when they should be used at runtime.
77
77
  - **Session sync** — Push local session history to the dashboard for review and recall.
78
78
  - **Vault secrets** — Store secrets server-side, commit only `clawdi://` references, and resolve them at runtime.
79
79
  - **App connections** — Hook agents into Notion, Gmail, Drive, Calendar, Linear, GitHub, and more from the dashboard. Tools show up inside every connected agent automatically over MCP.
@@ -90,7 +90,8 @@ Later, in a different agent or a fresh session, ask "what package manager should
90
90
  Run a fullstack dev command with vault references without putting plaintext secrets on disk:
91
91
 
92
92
  ```bash
93
- clawdi vault set OPENAI_API_KEY
93
+ printf '%s\n' "$OPENAI_API_KEY" | clawdi vault set OPENAI_API_KEY --stdin
94
+ clawdi vault import --vault prod --section stripe --project personal --yes .env.stripe
94
95
  echo "OPENAI_API_KEY=clawdi://project/<project-id>/vault/default/field/OPENAI_API_KEY" > .env.clawdi
95
96
  clawdi run --dry-run --env-file .env.clawdi -- npm run dev
96
97
  clawdi run --env-file .env.clawdi -- npm run dev
@@ -99,7 +100,7 @@ clawdi inject --dry-run --in .env.clawdi --out .env.local
99
100
  clawdi inject --force --in .env.clawdi --out .env.local
100
101
  ```
101
102
 
102
- `clawdi vault set`, `clawdi vault import`, and `clawdi vault list` print exact references that include the Project ID. Project-relative references such as `clawdi://default/OPENAI_API_KEY` still work for portable templates, but exact references are the default copy/read UX.
103
+ `clawdi vault set`, `clawdi vault import`, `clawdi vault rm`, and `clawdi vault list` print the concrete Project target or exact references that include the Project ID. `vault set` supports `--value` and `--stdin` for scripts; `vault import` supports `--vault`, `--section`, `--project`, and warns about skipped invalid dotenv identifiers. Project-relative references such as `clawdi://default/OPENAI_API_KEY` still work for portable templates, but exact references are the default copy/read UX.
103
104
 
104
105
  Agents should prefer `clawdi run --env-file .env.clawdi -- <command>` when they can launch the tool themselves. Use `clawdi inject` only for tools that must read a physical `.env.local`; generated files are written owner-only and should stay gitignored.
105
106
 
@@ -128,7 +129,7 @@ clawdi skill install anthropics/skills/artifacts-builder
128
129
 
129
130
  ## Roadmap
130
131
 
131
- Today Clawdi gives one person a shared layer across their agents. Two bigger bets come next.
132
+ Today Clawdi gives individuals and read-only Project collaborators a shared layer across their agents. Two bigger bets come next.
132
133
 
133
134
  The first is autonomy. Agents should work without you at the keyboard.
134
135
 
@@ -136,9 +137,10 @@ The first is autonomy. Agents should work without you at the keyboard.
136
137
  - Remote control for agents on any of your machines.
137
138
  - Automatic memory built from session history.
138
139
 
139
- The second is making Clawdi multi-player. Project sharing now covers read-only Project access in the CLI/backend; dashboard surfaces and richer team roles come next.
140
+ The second is deepening multi-player workflows beyond read-only Project sharing.
140
141
 
141
- - Shared memory, skills, and connections, with broader access controls.
142
+ - Richer team roles and broader access controls.
143
+ - Shared memory, skills, and connections.
142
144
  - An agent-to-agent channel for handoff and ask-for-help.
143
145
  - Task tracking that every connected agent can use.
144
146
 
@@ -243,11 +245,13 @@ Each agent has a dedicated adapter in [`packages/cli/src/adapters`](https://gith
243
245
  | --- | --- |
244
246
  | `clawdi auth login` / `logout` | Authenticate this machine |
245
247
  | `clawdi status [--json]` | Show auth and sync state |
248
+ | `clawdi config list/get/set/unset` | Read or write CLI configuration |
246
249
  | `clawdi setup [--agent <type>] [--no-daemon]` | Register local agents, install MCP, install the bundled skill, and install/start daemons by default |
247
250
  | `clawdi teardown [--agent <type>]` | Remove Clawdi's local agent wiring |
248
251
  | `clawdi daemon run/install/status/logs/doctor/restart/uninstall` | Run and manage the background sync daemon (`serve` remains a legacy alias) |
249
252
  | `clawdi push` | Upload sessions and skills |
250
253
  | `clawdi pull` | Download cloud skills into registered agents |
254
+ | `clawdi session list/extract` | Inspect local agent sessions |
251
255
  | `clawdi memory list/search/add/rm` | Manage cross-agent long-term memory |
252
256
  | `clawdi skill list/add/install/rm/init` | Manage portable skills |
253
257
  | `clawdi project create/list/show/share/share-links/invite/invites/members/leave/unshare` | Manage Projects and read-only sharing |
@@ -255,15 +259,15 @@ Each agent has a dedicated adapter in [`packages/cli/src/adapters`](https://gith
255
259
  | `clawdi agent projects list/attach/detach/move` | View the fixed Agent Project and manage attached Projects |
256
260
  | `clawdi agent credentials import/materialize` | Sync local CLI credential profiles for Codex, Claude Code, and GitHub CLI; explicit Keychain import requires service/account options |
257
261
  | `clawdi project folder link/status/unlink` | Link a local folder to a Project for vault reference selection |
258
- | `clawdi vault set/list/import` | Manage encrypted secrets and copy exact references |
262
+ | `clawdi vault set/list/import/rm` | Manage encrypted secrets and copy exact references |
259
263
  | `clawdi read <clawdi://...>` | Explicitly print one vault reference value |
260
264
  | `clawdi inject --in <file> --out <file>` | Render `clawdi://` references into templates |
261
265
  | `clawdi run --env-file <file> -- <cmd>` | Run a command with explicit vault references resolved |
262
266
  | `clawdi doctor` | Diagnose auth, agent paths, vault, and MCP config |
263
267
  | `clawdi update` | Install the latest CLI version (`--check` only reports) |
268
+ | `clawdi mcp` | Start the MCP stdio server used by agents |
264
269
 
265
270
  Auto-update is enabled by default for all newer releases, including majors. Human CLI invocations update the global CLI in the background; installed daemons check on their own cadence, install silently, then let launchd/systemd restart them onto the new code. Disable both with `CLAWDI_NO_AUTO_UPDATE=1` or `clawdi config set autoUpdate false`.
266
- | `clawdi mcp` | Start the MCP stdio server used by agents |
267
271
 
268
272
  Every command supports `--help`.
269
273