@botbotgo/agent-harness 0.0.19 → 0.0.21

package/README.md

@@ -1,21 +1,27 @@
 # @botbotgo/agent-harness
 
-## Slogan
+## Product Overview
 
-Declarative agent workspaces for LangChain v1 and DeepAgents.
+`@botbotgo/agent-harness` helps developers build complex agent-based applications fast and keep them easy to maintain.
 
-## Product Overview
+It helps developers:
 
-`@botbotgo/agent-harness` is a TypeScript framework for loading a local workspace from disk, compiling it into runnable agent bindings, and executing requests through either a LangChain v1 path or a DeepAgent path.
+- define agents in YAML
+- keep workspace behavior in `config/workspace.yaml`
+- keep shared bootstrap context in `config/agent-context.md`
+- discover tools and skills from `resources/`
+- run through either LangChain v1 or DeepAgents with one app-facing API
 
-The framework is workspace-first:
+Why it works:
 
-- agents are declared in YAML
-- tools and skills are discovered from `resources/`
-- workspace-wide behavior is declared in `config/workspace.yaml`
-- agent bootstrap context is declared in `config/agent-context.md`
+- it helps developers move from idea to working complex agent application with less setup friction
+- it makes ongoing maintenance lighter, including maintenance flows that can be automated by the application itself
+- one workspace becomes the source of truth for agent topology, models, tools, and operating context
+- one API covers direct agents and orchestration flows
+- local resources stay portable and versionable
+- thread state, approvals, resumability, and maintenance are built in
 
-The public API stays intentionally small:
+Core API:
 
 - `createAgentHarness(...)`
 - `run(...)`
@@ -45,6 +51,7 @@ your-workspace/
   resources/
     package.json
     tools/
+    skills/
 ```
 
 Minimal usage:
@@ -68,15 +75,12 @@ try {
 
 ## Feature List
 
-- Declarative `Model`, `EmbeddingModel`, `VectorStore`, `LangChainAgent`, `DeepAgent`, and `Runtime` objects
-- Workspace loading from disk with framework defaults and workspace overrides
-- LangChain v1 agents for lightweight tool-calling flows
-- DeepAgents for planning, filesystem-backed execution, subagents, skills, and long-term memory
-- Resource package loading from `resources/tools/` and `resources/skills/`
-- Host-agent routing between a direct lane and an orchestration lane
-- Persistent thread state, approvals, run history, and resumable execution
-- Store-backed `/memories/*` long-term memory
-- Background checkpoint maintenance for `SqliteSaver`
+- One workspace for agents, models, tools, and runtime behavior
+- One API for both LangChain v1 and DeepAgents
+- Built-in routing for direct and orchestration flows
+- Auto-discovered local tools and skills from `resources/tools/` and `resources/skills/`
+- Built-in thread state, approvals, resumable runs, and long-term memory
+- MCP server helpers plus background checkpoint maintenance
 
 ## How To Use
 
@@ -192,10 +196,12 @@ Use this file for workspace-wide behavior such as:
 
 ### `config/agent-context.md`
 
-Use this file for shared bootstrap context that agents should read at construction time.
+Use this file for shared bootstrap context that agents read at construction time.
 
 Put stable project context here, not long-term mutable memory.
 
+If a runnable app workspace also includes `AGENTS.md`, treat that file as workspace-level operating guidance. It complements `config/agents/*.yaml`: `AGENTS.md` carries durable behavioral rules, while `config/agents/` defines agent topology and runtime configuration.
+
 ### Agent YAML
 
 Use `config/agents/*.yaml` to configure agents. Common fields include:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@botbotgo/agent-harness",
-  "version": "0.0.19",
+  "version": "0.0.21",
   "description": "Agent Harness framework package",
   "type": "module",
   "packageManager": "npm@10.9.2",