agentix-cli 0.5.0 → 0.6.0

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 +14 -0
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -195,8 +195,22 @@ Total budget: 4000 tokens. Lower layers truncated if over budget.
195
195
  | `/task` | POST | `{ "agent": "id", "message": "..." }` |
196
196
  | `/mesh/task` | POST | `{ "peer": "name", "message": "..." }` |
197
197
  | `/webhook/:agentId[/:source]` | POST | Webhook callback (GitLab, GitHub, Stripe, Sentry) |
198
+ | `/v1/chat/completions` | POST | OpenAI-compatible endpoint (ElevenLabs, Cursor, any client) |
199
+ | `/llm/:agentId/v1/chat/completions` | POST | OpenAI-compatible with explicit agent |
198
200
  | `/.well-known/agent-card.json` | GET | A2A agent discovery |
199
201
 
202
+ ## OpenAI-Compatible Endpoint
203
+
204
+ Any agent can be used as an LLM backend for ElevenLabs Conversational AI, Cursor, or any OpenAI-compatible client.
205
+
206
+ ```bash
207
+ curl -X POST http://your-server:18800/v1/chat/completions \
208
+ -H "Content-Type: application/json" \
209
+ -d '{"model": "atlas", "messages": [{"role": "user", "content": "Hello"}]}'
210
+ ```
211
+
212
+ Supports streaming (`"stream": true`) with SSE. The `model` field maps to the agent ID.
213
+
200
214
  ## Three execution tiers
201
215
 
202
216
  | Tier | How | Auth | Best for |
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "agentix-cli",
3
- "version": "0.5.0",
3
+ "version": "0.6.0",
4
4
  "description": "Self-hosted multi-agent orchestrator — routes Telegram, WhatsApp, crons, and A2A mesh tasks to Claude Code, OpenAI, or any LLM provider",
5
5
  "license": "MIT",
6
6
  "author": {