hyperterse 2.3.0 → 2.5.0
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.
- package/README.md +54 -22
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
<!-- Start of - Dont change this block -->
|
|
2
2
|
<div align="center">
|
|
3
3
|
<picture>
|
|
4
|
-
<img alt="Hyperterse
|
|
4
|
+
<img alt="Hyperterse — The agentic server framework." src="docs/assets/og.png" />
|
|
5
5
|
</picture>
|
|
6
6
|
</div>
|
|
7
7
|
<br />
|
|
@@ -9,7 +9,7 @@
|
|
|
9
9
|
<h1>Hyperterse</h1>
|
|
10
10
|
</div>
|
|
11
11
|
<p align="center">
|
|
12
|
-
<strong>The
|
|
12
|
+
<strong>The agentic server framework.</strong><br />
|
|
13
13
|
<a href="https://hyperterse.com">Website</a>
|
|
14
14
|
•
|
|
15
15
|
<a href="https://docs.hyperterse.com">Documentation</a>
|
|
@@ -25,21 +25,30 @@
|
|
|
25
25
|
|
|
26
26
|
<!-- End of - Dont change this block -->
|
|
27
27
|
|
|
28
|
-
Hyperterse is
|
|
28
|
+
**Hyperterse** is an **agentic server framework**: one build ships **agents** (A2A), **tools** (MCP), **prompts**, **resources**, database adapters, auth, caching, and observability from a single process. You declare surfaces in config; the compiler validates and bundles them. Clients use [MCP](https://modelcontextprotocol.io/) Streamable HTTP at `/mcp` for tools, prompts, and resources; [A2A](https://github.com/a2aproject/a2a-go)-style agent routes live at `/agent/{name}` when you define agents.
|
|
29
29
|
|
|
30
|
-
|
|
30
|
+
## Where to start
|
|
31
|
+
|
|
32
|
+
- **Agents** — Declarative agents and A2A: [Agents overview](https://docs.hyperterse.com/agents/overview), [Agents quickstart](https://docs.hyperterse.com/agents/quickstart).
|
|
33
|
+
- **Tools** — Callable MCP tools (DB or scripts): [Tools](https://docs.hyperterse.com/concepts/tools), [Scripts](https://docs.hyperterse.com/concepts/scripts), [Adapters](https://docs.hyperterse.com/concepts/adapters).
|
|
34
|
+
- **Resources** — Static context for clients: [Resources](https://docs.hyperterse.com/concepts/resources).
|
|
35
|
+
- **Prompts** — Reusable prompt templates: [Prompts](https://docs.hyperterse.com/concepts/prompts).
|
|
36
|
+
|
|
37
|
+
The [Quickstart](https://docs.hyperterse.com/quickstart) walks through install, scaffold, and run, then optional MCP tool checks.
|
|
31
38
|
|
|
32
39
|
## What Hyperterse is for
|
|
33
40
|
|
|
34
|
-
-
|
|
35
|
-
-
|
|
36
|
-
-
|
|
41
|
+
- Running **agents** alongside **MCP tools**, **prompts**, and **resources** in one deployable service
|
|
42
|
+
- Exposing database queries and custom logic as MCP tools with declarative config
|
|
43
|
+
- Production **Streamable HTTP** for MCP and **A2A** routes for agents
|
|
44
|
+
- TypeScript handlers and transforms where config alone is not enough
|
|
37
45
|
|
|
38
46
|
## Core capabilities
|
|
39
47
|
|
|
40
|
-
- **
|
|
48
|
+
- **Agents**: declarative configs, tool-access policies, multi-provider models, per-agent A2A HTTP.
|
|
49
|
+
- **Filesystem discovery**: one MCP tool per tool definition; prompts and resources follow the same discover-and-compile model (see [Project structure](https://docs.hyperterse.com/concepts/project-structure)).
|
|
41
50
|
- **Execution models**: DB-backed tools (`use` + `statement`) or script-backed tools (`handler`).
|
|
42
|
-
- **Database adapters**: PostgreSQL, MySQL, MongoDB, Redis.
|
|
51
|
+
- **Database adapters**: PostgreSQL, MySQL, SQLite, MongoDB, Redis.
|
|
43
52
|
- **Per-tool auth**: built-in `allow_all` and `api_key`, plus custom plugins.
|
|
44
53
|
- **In-memory caching**: global defaults + per-tool overrides.
|
|
45
54
|
- **Observability**: OpenTelemetry tracing/metrics + structured logging.
|
|
@@ -63,9 +72,11 @@ Generated starter structure:
|
|
|
63
72
|
```text
|
|
64
73
|
.
|
|
65
74
|
├── .hyperterse
|
|
66
|
-
├── .
|
|
75
|
+
├── .agents/
|
|
67
76
|
│ └── skills/
|
|
68
|
-
│
|
|
77
|
+
│ ├── hyperterse-docs/
|
|
78
|
+
│ │ └── SKILL.md
|
|
79
|
+
│ └── hyperterse-agents/
|
|
69
80
|
│ └── SKILL.md
|
|
70
81
|
└── app/
|
|
71
82
|
└── tools/
|
|
@@ -98,7 +109,7 @@ Expected response:
|
|
|
98
109
|
{ "success": true }
|
|
99
110
|
```
|
|
100
111
|
|
|
101
|
-
###
|
|
112
|
+
### Optional: list MCP tools
|
|
102
113
|
|
|
103
114
|
```bash
|
|
104
115
|
curl -s -X POST http://localhost:8080/mcp \
|
|
@@ -115,7 +126,7 @@ By design, Hyperterse exposes two transport-layer tools:
|
|
|
115
126
|
- `search` - discover project tools by natural language
|
|
116
127
|
- `execute` - execute a project tool by name
|
|
117
128
|
|
|
118
|
-
###
|
|
129
|
+
### Optional: discover project tools (search)
|
|
119
130
|
|
|
120
131
|
```bash
|
|
121
132
|
curl -s -X POST http://localhost:8080/mcp \
|
|
@@ -245,7 +256,9 @@ Each tool must define exactly one execution mode:
|
|
|
245
256
|
|
|
246
257
|
## Runtime model
|
|
247
258
|
|
|
248
|
-
|
|
259
|
+
**MCP** — Streamable HTTP at `/mcp` (JSON-RPC 2.0): tools, prompts, resources, completion, subscriptions. See [MCP transport](https://docs.hyperterse.com/runtime/mcp-transport).
|
|
260
|
+
|
|
261
|
+
**A2A** — JSON-RPC per agent at `/agent/{agentName}` (agent card, messaging, tasks, streaming). See [A2A transport](https://docs.hyperterse.com/runtime/a2a-transport) and [Agents](https://docs.hyperterse.com/agents/overview).
|
|
249
262
|
|
|
250
263
|
Execution pipeline:
|
|
251
264
|
|
|
@@ -256,6 +269,25 @@ Execution pipeline:
|
|
|
256
269
|
5. Output transform (optional)
|
|
257
270
|
6. Response serialization
|
|
258
271
|
|
|
272
|
+
## MCP spec compliance
|
|
273
|
+
|
|
274
|
+
Hyperterse implements the [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) specification **[2025-11-25](https://modelcontextprotocol.io/specification/2025-11-25)**.
|
|
275
|
+
|
|
276
|
+
Compliance status by component:
|
|
277
|
+
|
|
278
|
+
| Spec component | Status |
|
|
279
|
+
| ----------------------------------------------------------------------------------------------------------------------------- | :----: |
|
|
280
|
+
| [Base protocol](https://modelcontextprotocol.io/specification/2025-11-25/basic) (JSON-RPC 2.0) | ✅ |
|
|
281
|
+
| [Lifecycle](https://modelcontextprotocol.io/specification/2025-11-25/basic/lifecycle) (initialize/initialized) | ✅ |
|
|
282
|
+
| [Tools](https://modelcontextprotocol.io/specification/2025-11-25/server/tools) (list, call, listChanged) | ✅ |
|
|
283
|
+
| [Resources](https://modelcontextprotocol.io/specification/2025-11-25/server/resources) (list, read, subscribe, updated) | ✅ |
|
|
284
|
+
| [Prompts](https://modelcontextprotocol.io/specification/2025-11-25/server/prompts) (list, get, listChanged) | ✅ |
|
|
285
|
+
| [Completion](https://modelcontextprotocol.io/specification/2025-11-25/server/utilities/completion) (ref/prompt, ref/resource) | ✅ |
|
|
286
|
+
| [Pagination](https://modelcontextprotocol.io/specification/2025-11-25/server/utilities/pagination) (cursor/nextCursor) | ⚠️ |
|
|
287
|
+
| Tool result content types (image, audio, resource_link) | ⚠️ |
|
|
288
|
+
|
|
289
|
+
Text content for tool results is supported; image, audio, and resource links are optional. Pagination applies when tools, prompts, or resources exceed typical small-to-medium counts.
|
|
290
|
+
|
|
259
291
|
## Security notes
|
|
260
292
|
|
|
261
293
|
- Use `{{ env.VAR_NAME }}` for secrets and connection strings.
|
|
@@ -268,16 +300,16 @@ Execution pipeline:
|
|
|
268
300
|
- [Introduction](https://docs.hyperterse.com/introduction)
|
|
269
301
|
- [Quickstart](https://docs.hyperterse.com/quickstart)
|
|
270
302
|
- [Project structure](https://docs.hyperterse.com/concepts/project-structure)
|
|
271
|
-
- [
|
|
272
|
-
- [
|
|
273
|
-
- [Resources](https://docs.hyperterse.com/concepts/resources)
|
|
274
|
-
- [
|
|
275
|
-
- [
|
|
303
|
+
- **Agents** — [Overview](https://docs.hyperterse.com/agents/overview), [Agents quickstart](https://docs.hyperterse.com/agents/quickstart), [Tool access](https://docs.hyperterse.com/agents/tool-access), [Runtime API](https://docs.hyperterse.com/agents/runtime-api), [Model providers](https://docs.hyperterse.com/agents/model-providers)
|
|
304
|
+
- **Tools** — [Tools](https://docs.hyperterse.com/concepts/tools), [Scripts](https://docs.hyperterse.com/concepts/scripts), [Adapters](https://docs.hyperterse.com/concepts/adapters)
|
|
305
|
+
- **Resources** — [Resources](https://docs.hyperterse.com/concepts/resources)
|
|
306
|
+
- **Prompts** — [Prompts](https://docs.hyperterse.com/concepts/prompts)
|
|
307
|
+
- [Authentication](https://docs.hyperterse.com/concepts/authentication)
|
|
276
308
|
- [MCP transport](https://docs.hyperterse.com/runtime/mcp-transport)
|
|
309
|
+
- [A2A transport](https://docs.hyperterse.com/runtime/a2a-transport)
|
|
277
310
|
- [Execution pipeline](https://docs.hyperterse.com/runtime/execution-pipeline)
|
|
278
311
|
- [CLI reference](https://docs.hyperterse.com/reference/cli)
|
|
279
|
-
- [Prompt config
|
|
280
|
-
- [Resource config reference](https://docs.hyperterse.com/reference/resource-config)
|
|
312
|
+
- [Agent config](https://docs.hyperterse.com/reference/agent-config), [Prompt config](https://docs.hyperterse.com/reference/prompt-config), [Resource config](https://docs.hyperterse.com/reference/resource-config)
|
|
281
313
|
- [Configuration schemas](https://docs.hyperterse.com/reference/configuration-schemas)
|
|
282
314
|
|
|
283
315
|
## Contributing
|
|
@@ -293,7 +325,7 @@ See `CONTRIBUTING.md` and `CODE_OF_CONDUCT.md`.
|
|
|
293
325
|
---
|
|
294
326
|
|
|
295
327
|
<p align="center">
|
|
296
|
-
|
|
328
|
+
Agentic server framework—agents, tools, prompts, resources, one engine.<br />
|
|
297
329
|
<a href="https://hyperterse.com">Website</a>
|
|
298
330
|
•
|
|
299
331
|
<a href="https://github.com/hyperterse/hyperterse">GitHub</a>
|