mcp-agent-foundry 2.2.0 → 2.4.0

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 +22 -22
  2. package/package.json +4 -4
package/README.md CHANGED
@@ -1,4 +1,4 @@
1
- # Agent Foundry
1
+ # Hari Seldon
2
2
 
3
3
  **Multi-Agent AI Orchestration with Git Worktree Isolation**
4
4
 
@@ -7,7 +7,7 @@
7
7
  [![npm version](https://img.shields.io/npm/v/mcp-agent-foundry.svg)](https://www.npmjs.com/package/mcp-agent-foundry)
8
8
  [![Tests](https://img.shields.io/badge/tests-passing-brightgreen.svg)](tests/)
9
9
 
10
- Agent Foundry extends Claude Code with multi-provider AI orchestration and git worktree isolation. Each coding agent receives its own isolated worktree - a separate checkout on a dedicated branch - enabling true parallel development without file conflicts. Get second opinions from external AI models without leaving Claude Code.
10
+ Hari Seldon extends Claude Code with multi-provider AI orchestration and git worktree isolation. Each coding agent receives its own isolated worktree - a separate checkout on a dedicated branch - enabling true parallel development without file conflicts. Get second opinions from external AI models without leaving Claude Code.
11
11
 
12
12
  ---
13
13
 
@@ -40,17 +40,17 @@ Install as a Claude Code plugin for slash commands and auto-invoked skills:
40
40
 
41
41
  ```bash
42
42
  # Add the marketplace
43
- claude plugin marketplace add github:sashabogi/agent-foundry
43
+ claude plugin marketplace add github:sashabogi/hari-seldon
44
44
 
45
45
  # Install the plugin
46
- claude plugin install agent-foundry
46
+ claude plugin install hari-seldon
47
47
  ```
48
48
 
49
49
  Restart Claude Code, then use:
50
50
  ```
51
- /agent-foundry:invoke critic "Review my authentication approach"
52
- /agent-foundry:review
53
- /agent-foundry:status
51
+ /hari-seldon:invoke critic "Review my authentication approach"
52
+ /hari-seldon:review
53
+ /hari-seldon:status
54
54
  ```
55
55
 
56
56
  ### Option 2: MCP Server Only
@@ -61,7 +61,7 @@ Install as an MCP server (no slash commands, just MCP tools):
61
61
  npm install -g mcp-agent-foundry
62
62
  ```
63
63
 
64
- Agent Foundry automatically registers with Claude Code during installation.
64
+ Hari Seldon automatically registers with Claude Code during installation.
65
65
  Restart Claude Code to activate.
66
66
 
67
67
  To verify: Run `/mcp` in Claude Code - you should see `agent-foundry · ✓ connected`
@@ -86,14 +86,14 @@ When installed as a Claude Code plugin, these slash commands are available:
86
86
 
87
87
  | Command | Description | Example |
88
88
  |---------|-------------|---------|
89
- | `/agent-foundry:invoke` | Invoke an agent by role | `/agent-foundry:invoke critic "Review this plan"` |
90
- | `/agent-foundry:review` | Get external code review | `/agent-foundry:review src/auth.ts` |
91
- | `/agent-foundry:critique` | Get plan/architecture critique | `/agent-foundry:critique` |
92
- | `/agent-foundry:compare` | Compare multiple agents | `/agent-foundry:compare coder,reviewer "Implement auth"` |
93
- | `/agent-foundry:status` | Show provider health | `/agent-foundry:status` |
94
- | `/agent-foundry:setup` | Configure providers | `/agent-foundry:setup` |
95
- | `/agent-foundry:pipeline` | Run multi-agent pipeline | `/agent-foundry:pipeline` |
96
- | `/agent-foundry:worktree` | Manage git worktrees | `/agent-foundry:worktree list` |
89
+ | `/hari-seldon:invoke` | Invoke an agent by role | `/hari-seldon:invoke critic "Review this plan"` |
90
+ | `/hari-seldon:review` | Get external code review | `/hari-seldon:review src/auth.ts` |
91
+ | `/hari-seldon:critique` | Get plan/architecture critique | `/hari-seldon:critique` |
92
+ | `/hari-seldon:compare` | Compare multiple agents | `/hari-seldon:compare coder,reviewer "Implement auth"` |
93
+ | `/hari-seldon:status` | Show provider health | `/hari-seldon:status` |
94
+ | `/hari-seldon:setup` | Configure providers | `/hari-seldon:setup` |
95
+ | `/hari-seldon:pipeline` | Run multi-agent pipeline | `/hari-seldon:pipeline` |
96
+ | `/hari-seldon:worktree` | Manage git worktrees | `/hari-seldon:worktree list` |
97
97
 
98
98
  ### Auto-Invoked Skills
99
99
 
@@ -161,7 +161,7 @@ The plugin also includes context-aware skills that Claude invokes automatically:
161
161
 
162
162
  ## Intelligent Failover System
163
163
 
164
- Agent Foundry includes automatic provider failover with health tracking:
164
+ Hari Seldon includes automatic provider failover with health tracking:
165
165
 
166
166
  ```
167
167
  ┌─────────────────────────────────────────────────────────────┐
@@ -214,7 +214,7 @@ Agent Foundry includes automatic provider failover with health tracking:
214
214
 
215
215
  ## Session Mode (Claude Code Users)
216
216
 
217
- When running inside Claude Code, Agent Foundry can delegate Anthropic-based roles back to the current session—no subprocess, no API key, no additional cost.
217
+ When running inside Claude Code, Hari Seldon can delegate Anthropic-based roles back to the current session—no subprocess, no API key, no additional cost.
218
218
 
219
219
  ### Quick Setup
220
220
 
@@ -227,7 +227,7 @@ providers:
227
227
 
228
228
  ### How It Works
229
229
 
230
- Instead of spawning a subprocess or making API calls, Agent Foundry returns a **delegation response** that the current Claude session handles directly:
230
+ Instead of spawning a subprocess or making API calls, Hari Seldon returns a **delegation response** that the current Claude session handles directly:
231
231
 
232
232
  - **orchestrator**, **reviewer**, **researcher** roles → Handled by current session
233
233
  - **critic**, **coder**, **designer** roles → External API calls (OpenAI, Gemini, etc.)
@@ -246,7 +246,7 @@ See [Session Delegation Architecture](docs/SESSION_DELEGATION.md) for complete d
246
246
 
247
247
  ## Hooks System
248
248
 
249
- Agent Foundry provides a flexible hooks system that lets you customize agent behavior by running commands at key lifecycle events.
249
+ Hari Seldon provides a flexible hooks system that lets you customize agent behavior by running commands at key lifecycle events.
250
250
 
251
251
  ### Supported Events
252
252
 
@@ -352,7 +352,7 @@ actions:
352
352
 
353
353
  ## Context Manager
354
354
 
355
- Agent Foundry includes intelligent context management to prevent token limit issues and optimize AI provider usage.
355
+ Hari Seldon includes intelligent context management to prevent token limit issues and optimize AI provider usage.
356
356
 
357
357
  ### Features
358
358
 
@@ -809,7 +809,7 @@ pnpm typecheck
809
809
 
810
810
  ### Debug Logging
811
811
 
812
- Agent Foundry provides enhanced debug logging controlled via environment variables:
812
+ Hari Seldon provides enhanced debug logging controlled via environment variables:
813
813
 
814
814
  ```bash
815
815
  # Enable debug logging
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "mcp-agent-foundry",
3
- "version": "2.2.0",
3
+ "version": "2.4.0",
4
4
  "description": "Multi-Agent AI Orchestration with Git Worktree Isolation for Claude Code",
5
5
  "type": "module",
6
6
  "main": "dist/index.js",
@@ -28,11 +28,11 @@
28
28
  },
29
29
  "repository": {
30
30
  "type": "git",
31
- "url": "git+https://github.com/sashabogi/agent-foundry.git"
31
+ "url": "git+https://github.com/sashabogi/hari-seldon.git"
32
32
  },
33
- "homepage": "https://github.com/sashabogi/agent-foundry#readme",
33
+ "homepage": "https://github.com/sashabogi/hari-seldon#readme",
34
34
  "bugs": {
35
- "url": "https://github.com/sashabogi/agent-foundry/issues"
35
+ "url": "https://github.com/sashabogi/hari-seldon/issues"
36
36
  },
37
37
  "keywords": [
38
38
  "mcp",