hoomanjs 1.12.0 → 1.12.1

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.
Files changed (2) hide show
  1. package/README.md +25 -17
  2. package/package.json +2 -2
package/README.md CHANGED
@@ -1,7 +1,7 @@
1
1
  <div align="center">
2
2
  <h1>Hooman</h1>
3
3
  <p>
4
- Hooman is a Bun-powered local AI agent CLI built with TypeScript, <a href="https://www.npmjs.com/package/@strands-agents/sdk">Strands Agents SDK</a>, and <a href="https://github.com/vadimdemedes/ink">Ink</a>.
4
+ Hooman is a hackable, Bun-powered AI agent toolkit for local workflows. It is built with TypeScript, <a href="https://www.npmjs.com/package/@strands-agents/sdk">Strands Agents SDK</a>, and <a href="https://github.com/vadimdemedes/ink">Ink</a>.
5
5
  </p>
6
6
  <p>
7
7
  <a href="https://bun.com"><img src="https://img.shields.io/badge/runtime-Bun-f9f1e1?logo=bun&logoColor=000000" alt="Bun" /></a>
@@ -16,12 +16,12 @@
16
16
  </p>
17
17
  </div>
18
18
 
19
- It gives you:
19
+ It gives you a practical toolkit to build and run agent workflows:
20
20
 
21
21
  - a one-shot `exec` command for single prompts
22
- - a stateful `chat` interface for interactive sessions
23
- - a `daemon` command for processing MCP channel notifications in background
24
- - an Ink-powered `configure` workflow for editing app config, `instructions.md`, MCP servers, and installed skills
22
+ - a stateful `chat` interface for iterative sessions
23
+ - a `daemon` command for channel-driven MCP automation
24
+ - an Ink-powered `configure` workflow for app config, prompts, MCP servers, and installed skills
25
25
  - an `acp` command for running Hooman as an Agent Client Protocol (ACP) agent over stdio
26
26
 
27
27
  ## Features
@@ -32,6 +32,7 @@ It gives you:
32
32
  - MCP server `instructions` support: server-provided instructions are appended to the agent system prompt
33
33
  - MCP channel notification support through `hooman daemon --channels`
34
34
  - Skill discovery / install / removal through the integrated configure flow
35
+ - Toolkit-oriented architecture with configurable tools, prompts, memory, and transports
35
36
  - Interactive terminal UI for chat and configuration
36
37
 
37
38
  ## Requirements
@@ -157,18 +158,20 @@ hooman daemon --channels --yolo
157
158
 
158
159
  ### Feature Flags
159
160
 
160
- Runtime tools and prompt sections are controlled from `config.json` under `features`:
161
+ Runtime tools and prompt sections are controlled from `config.json` under `tools`:
161
162
 
162
- - `features.fetch.enabled`
163
- - `features.filesystem.enabled`
164
- - `features.shell.enabled`
165
- - `features.ltm.enabled`
166
- - `features.wiki.enabled`
163
+ - `tools.fetch.enabled`
164
+ - `tools.filesystem.enabled`
165
+ - `tools.shell.enabled`
166
+ - `tools.ltm.enabled`
167
+ - `tools.wiki.enabled`
168
+ - `tools.mcp.enabled` (enables MCP management tools + prefixed MCP server tools/instructions)
169
+ - `tools.skills.enabled` (enables skills management tools + skills prompt sections)
167
170
 
168
171
  Both `ltm` and `wiki` include dedicated Chroma settings under:
169
172
 
170
- - `features.ltm.chroma` (default collection: `memory`)
171
- - `features.wiki.chroma` (default collection: `wiki`)
173
+ - `tools.ltm.chroma` (default collection: `memory`)
174
+ - `tools.wiki.chroma` (default collection: `wiki`)
172
175
 
173
176
  ### `hooman configure`
174
177
 
@@ -211,7 +214,7 @@ Hooman stores its data in:
211
214
 
212
215
  Important files and folders:
213
216
 
214
- - `config.json` - app name, LLM provider/model, tool approvals, feature flags, LTM/wiki settings, compaction
217
+ - `config.json` - app name, LLM provider/model, tool flags, LTM/wiki settings, compaction
215
218
  - `instructions.md` - system instructions used to build the agent prompt
216
219
  - `mcp.json` - MCP server definitions
217
220
  - `skills/` - installed skills
@@ -231,9 +234,6 @@ This is the shape managed by `hooman configure`:
231
234
  "params": {}
232
235
  },
233
236
  "tools": {
234
- "allowed": []
235
- },
236
- "features": {
237
237
  "fetch": {
238
238
  "enabled": true
239
239
  },
@@ -260,6 +260,12 @@ This is the shape managed by `hooman configure`:
260
260
  "wiki": "wiki"
261
261
  }
262
262
  }
263
+ },
264
+ "mcp": {
265
+ "enabled": false
266
+ },
267
+ "skills": {
268
+ "enabled": false
263
269
  }
264
270
  },
265
271
  "compaction": {
@@ -269,6 +275,8 @@ This is the shape managed by `hooman configure`:
269
275
  }
270
276
  ```
271
277
 
278
+ Tool approvals are session-scoped and are not persisted in `config.json`.
279
+
272
280
  Supported `llm.provider` values:
273
281
 
274
282
  - `ollama`
package/package.json CHANGED
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "name": "hoomanjs",
3
- "version": "1.12.0",
4
- "description": "Bun-powered local AI agent CLI with chat, exec, ACP, MCP, and skills support.",
3
+ "version": "1.12.1",
4
+ "description": "Hackable Bun-powered AI agent toolkit for building local CLI, ACP, MCP, and channel-driven workflows.",
5
5
  "author": {
6
6
  "name": "Vaibhav Pandey",
7
7
  "email": "contact@vaibhavpandey.com"