Skip to content

Commit f11968c

Browse files
committed
feat: add API class citations and related links to emergent capabilities doc
Linked ForgeToolMetaTool, EmergentCapabilityEngine, EmergentJudge, EmergentToolRegistry, ComposableToolBuilder, CodeSandbox API classes inline throughout the document. Added related links section with cross-references to blog posts, feature docs, and API reference pages.
1 parent 3c1e6b5 commit f11968c

1 file changed

Lines changed: 17 additions & 8 deletions

File tree

docs/architecture/EMERGENT_CAPABILITIES.md

Lines changed: 17 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
1-
# Emergent Capabilities
1+
# Emergent Capabilities: Runtime Tool Forging
22

3-
Agents with `emergent: true` can forge new tools at runtime when no existing capability fits the task. The agent calls the `forge_tool` meta-tool, which builds, tests, and judge-reviews the tool before making it available.
3+
Agents with `emergent: true` can forge new tools at runtime when no existing capability fits the task. The agent calls the [`forge_tool`](/api/classes/ForgeToolMetaTool) meta-tool, which builds, tests, and judge-reviews the tool before making it available. The system is implemented across three core classes: [`EmergentCapabilityEngine`](/api/classes/EmergentCapabilityEngine), [`EmergentJudge`](/api/classes/EmergentJudge), and [`EmergentToolRegistry`](/api/classes/EmergentToolRegistry).
44

55
## Quick Start
66

@@ -50,9 +50,9 @@ await agent.initialize({
5050

5151
## Two Creation Modes
5252

53-
### Compose Mode Chain Existing Tools
53+
### Compose Mode -- Chain Existing Tools
5454

55-
The safest default. Compose mode builds a pipeline of existing registered tools. No sandbox is needed because it only invokes tools the agent already has access to.
55+
The safest default. Compose mode uses the [`ComposableToolBuilder`](/api/classes/ComposableToolBuilder) to chain existing registered tools into a pipeline. No sandbox is needed because it only invokes tools the agent already has access to.
5656

5757
**Example: Research-and-summarize pipeline**
5858

@@ -153,9 +153,9 @@ const forgeRequest = {
153153
}
154154
```
155155

156-
### Sandbox Mode Write Novel Code
156+
### Sandbox Mode -- Write Novel Code
157157

158-
Sandbox mode runs agent-written JavaScript in an isolated V8 context with hard memory and timeout limits. More powerful but requires explicit opt-in.
158+
Sandbox mode runs agent-written JavaScript in an isolated V8 context via [`CodeSandbox`](/api/classes/CodeSandbox) with hard memory and timeout limits. More powerful but requires explicit opt-in.
159159

160160
**Example: CSV parser**
161161

@@ -289,7 +289,7 @@ These are rejected at code validation time (before execution):
289289

290290
## LLM-as-Judge Verification
291291

292-
Every forged tool undergoes LLM-as-judge review. No tool activates without judge approval.
292+
Every forged tool undergoes review by the [`EmergentJudge`](/api/classes/EmergentJudge). No tool activates without judge approval.
293293

294294
| Review stage | When | What it checks |
295295
|---|---|---|
@@ -301,7 +301,7 @@ If no LLM callback is configured for the judge, **creation review fails closed**
301301

302302
## Tiered Promotion
303303

304-
Tools start at session tier and can be promoted as they prove reliability:
304+
Tools start at session tier in the [`EmergentToolRegistry`](/api/classes/EmergentToolRegistry) and can be promoted as they prove reliability:
305305

306306
```
307307
session ──(5+ uses, >0.8 confidence, panel approved)──→ agent ──(human approval)──→ shared
@@ -483,3 +483,12 @@ await importEmergentTool('./slugify.emergent-tool.yaml', { seedId: agentSeedId }
483483
- Human approval is required for shared-tier promotion
484484
- Raw sandbox source is redacted at rest by default
485485
- If no LLM is configured, all forge requests are rejected (fail-closed)
486+
487+
## Related
488+
489+
- [Adaptive vs. Emergent Intelligence](https://agentos.sh/blog/adaptive-vs-emergent) -- how adaptive and emergent behavior differ in the AgentOS architecture
490+
- [Self-Improving Agents](/features/self-improving-agents) -- broader patterns for agents that improve over time
491+
- [Recursive Self-Building](/features/recursive-self-building) -- recursive tool creation and agent spawning
492+
- [Guardrails](/features/guardrails) -- safety mechanisms that constrain emergent behavior
493+
- [Agency API](/features/agency-api) -- multi-agent coordination strategies
494+
- **API Reference:** [`EmergentCapabilityEngine`](/api/classes/EmergentCapabilityEngine) | [`EmergentJudge`](/api/classes/EmergentJudge) | [`EmergentToolRegistry`](/api/classes/EmergentToolRegistry) | [`ForgeToolMetaTool`](/api/classes/ForgeToolMetaTool) | [`ComposableToolBuilder`](/api/classes/ComposableToolBuilder) | [`CodeSandbox`](/api/classes/CodeSandbox)

0 commit comments

Comments
 (0)