A local-first multi-agent app development platform, built on PenguinHarness
Commits on main
feat(blog): a Perspectives category and three posts on harness design and agent infrastructure (#45)
7617374 Yaowei Zheng committed 4 months ago
docs(changelog): 0.2.0 entries for the July 22 batch (#30)
9767fe6 Yaowei Zheng committed 4 months ago
feat: AgentHub 0.4.1 and a model-catalog refresh across every provider group (#43)
0f6828e Yaowei Zheng committed 4 months ago
feat(web): settings form polish — dialog layout, homepage button, no default rows, unified dropdown text (#39)
d01d0fa Yaowei Zheng committed 4 months ago
docs(blog): align intro with self-evolving example and soften exact scores (#42)
6d56ce9 Zhang Jason committed 4 months ago
feat: session source in session_meta and an Automated sidebar folder (#40)
c380113 Yaowei Zheng committed 4 months ago
fix(web): keep chat dropdown menus inside the viewport on mobile (#41)
e0bf170 Yaowei Zheng committed 4 months ago
feat(web): collapsed-rail nav with last conversation, new chat, and localized tooltips (#36)
45b5555 Yaowei Zheng committed 4 months ago
fix(web): render the subagent expansion below the tool call's own content (#33)
9a1257b Yaowei Zheng committed 4 months ago
feat(web): sidebar group polish — even hover geometry, folder open/close icons, group pinning (#35)
829ca57 Yaowei Zheng committed 4 months ago
feat(web): drop "none" from the offered thinking levels (#34)
78a8b35 Yaowei Zheng committed 4 months ago
feat(core): subagents inherit the parent session's model and thinking level (#38)
1514cd6 Yaowei Zheng committed 4 months ago
fix(web): usage chart tooltip at the pointer's lower-right + cache hit rate in the Cache Read bubble (#37)
cf27b13 Yaowei Zheng committed 4 months ago
feat: per-model max output tokens and a conversation-time thinking level backed by agent settings (#28)
cabbab1 Yaowei Zheng committed 4 months ago
feat(web): group the chat sidebar by workspace with an agent-mode toggle (#26)
99f391f Yaowei Zheng committed 4 months ago
feat(blog): grouped list, pinned posts, author/date/copy-link metadata (#20)
3806e4e Yaowei Zheng committed 4 months ago
fix(server): validate positiveIntParam and optionalDateParam inputs (#10)
85f8b9b Zhang Jason committed 4 months ago
test(core): cover CappedTextBuffer and ToolCallIdAllocator (#9)
7e0525a Zhang Jason committed 4 months ago
[fix(web)] localize copied task-stats line instead of hardcoded Chinese (#8)
1425b2f Zhang Jason committed 4 months ago
docs(examples): make self-improvement demo genuinely self-evolving (#29)
81d8c00 Zhang Jason committed 4 months ago
feat(web): letter avatars for custom model groups and agents (#31)
6d25adf Yaowei Zheng committed 4 months ago
feat(core): reserved-port and API-key guardrails in the default system prompt (#24)
c9cd1f9 Yaowei Zheng committed 4 months ago
feat(web): chat model picker lists key-configured models first, with a show-all expander (#22)
849f2fa Yaowei Zheng committed 4 months ago
feat(skills): vLLM and Ollama deployment plus LlamaFactory fine-tuning skills (#19)
636b25b Yaowei Zheng committed 4 months ago
[blog] add "Implementing Agent Self-Improvement with PenguinHarness on an AMD GPU" blog (#32)
cb283b6 GaoYuYang committed 4 months ago
docs: list the built-in Skills in the READMEs and on the landing page (#23)
0ad911a Yaowei Zheng committed 4 months ago
fix(web): chat links open in a new tab and long URLs/CJK wrap cleanly (#27)
cb22cd5 Yaowei Zheng committed 4 months ago
fix(site): make the docs and landing navbars identical (#25)
6d9a631 Yaowei Zheng committed 4 months ago
fix(llm): omit empty tools and keep tool_choice off the wire (#21)
ea0549b Yaowei Zheng committed 4 months ago