| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| README.md | 2026-04-18 | 2.8 kB | |
| v1.2.0 source code.tar.gz | 2026-04-18 | 260.3 kB | |
| v1.2.0 source code.zip | 2026-04-18 | 346.8 kB | |
| Totals: 3 Items | 609.9 kB | 2 | |
First minor release since 1.1.0. MCP integration, three new LLM providers, context management strategies, a CLI, tool output cost controls, and fixes for abort and error propagation.
Features
-
MCP integration. New
connectMCPTools()wires any MCP server (stdio) directly into agent tool use.@modelcontextprotocol/sdkis an optional peer dependency. Runnable example atexamples/16-mcp-github.ts. (#89, by @ibrahimkzmv) -
Three new LLM providers. First-class
provider: 'deepseek'(deepseek-chat,deepseek-reasoner),provider: 'minimax'(global and China endpoints viaMINIMAX_BASE_URL), and verified Groq via OpenAI-compatiblebaseURLinexamples/19-groq.ts. (#113 and [#114] by @hkalex; [#121] by @mvanhorn) -
Context management strategies. New
AgentConfig.contextStrategykeeps long runs under token ceilings with four strategies:sliding-window,summarize,compact(rule-based, no extra LLM call), andcustom. (#88 by @ibrahimkzmv; [#111], [#119] by @JackChen-me) -
Tool output cost controls. New
AgentConfig.maxToolOutputCharsand per-toolToolDefinition.maxOutputCharstruncate large outputs (head + tail with a marker). NewAgentConfig.compressToolResultscompresses older tool results once the agent has moved on; errors are never compressed. (#110, [#115], [#116], [#117], [#118] by @JackChen-me) -
CLI (
oma). New binary for shell and CI withoma run,oma task,oma provider, JSON-first output, and stable exit codes. Docs atdocs/cli.md. (#107 by @ibrahimkzmv) -
AgentConfig.customTools. Inject tool definitions at config time from the orchestrator. Bypasses preset/allowlist filtering but still respectsdisallowedTools. (#109, [#112] by @JackChen-me) -
globbuilt-in tool. Find files by glob pattern, sorted by modification time. (#102 by @ibrahimkzmv)
Fixes
-
AbortSignalpropagation. Abort now reaches tool execution, the Gemini adapter, and the abort queue path. (#104 fixes [#99], [#100], [#101], by @JackChen-me) -
Error event propagation.
AgentRunner.run()now surfaces error events to callers. (#103 fixes [#98], by @JackChen-me)
Examples
examples/16-mcp-github.ts: full MCP wiringexamples/17-minimax.ts,examples/18-deepseek.ts,examples/19-groq.ts: provider quickstartsexamples/with-vercel-ai-sdk/: Next.js + OMArunTeam()+ AI SDKuseChat
Docs
- READMEs (EN/ZH) expanded: CLI, MCP, context strategies, tool output control,
customTools. ZH caught up with EN on items that shipped in 1.1.
Install
:::bash
npm install @jackchen_me/open-multi-agent@1.2.0
Thanks to @hkalex, @ibrahimkzmv, and @mvanhorn for the external contributions that make this release.
Full changelog: https://github.com/JackChen-me/open-multi-agent/compare/v1.1.0...v1.2.0