| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| README.md | 2026-05-29 | 1.9 kB | |
| v2.8.0 source code.tar.gz | 2026-05-29 | 9.1 MB | |
| v2.8.0 source code.zip | 2026-05-29 | 9.4 MB | |
| Totals: 3 Items | 18.5 MB | 1 | |
What's New in v2.8.0
A feature release adding new Forge tools, a pluggable system-prompt base class, automatic context-window trimming, and a rewritten Claude plugin — plus the multi-agent deep-research example.
Core framework
Features
BaseSystemPromptGenerator— new abstract base class so you can build custom system-prompt generators;SystemPromptGeneratornow subclasses it (fully backwards compatible).- Automatic context trimming —
AtomicAgentgainsmax_context_tokensto auto-trim history and prevent context-window overruns.
Bug Fixes
- Prevent
Nonein MCP prompt text extraction from causing astr.joinTypeError (#252).
Atomic Forge — new tools
- arxiv_search — academic paper search via the public arXiv API
- datetime_tool — timezone-aware now / parse / convert / shift / diff
- hackernews_search — Hacker News search via the free Algolia API
- pdf_reader — PDF text + metadata extraction (local file or URL, page-range support)
- weather — current conditions and daily/hourly forecast via Open-Meteo (no key)
- wikipedia_search — Wikipedia search in any language edition (no key)
- fia_signals — crypto market intelligence (regime, signals, yields, gas, trending, wallet risk)
Tooling & examples
- Claude plugin v2 — rewritten as a skills-only pack with
create-atomic-*skills (agent, tool, schema, context-provider) and anatomic-explorersubagent for codebase mapping; fewer atomic-reviewer false positives. - deep-research example — rebuilt as a proper multi-agent research pipeline (planner, decider, extractor, reflector, writer, QA) with a restored chat loop.
- docs — clarified tool philosophy and the two patterns for using tools.
Full Changelog
https://github.com/BrainBlend-AI/atomic-agents/compare/v2.7.5...v2.8.0