Build and run agents you can see, understand and trust.
Python agentchatbotlarge-language-modelsllmllm-agentmcpmulti-agentmulti-modalreact-agentrealtime-agentvoice-agentvoice-assistant
Commits on main
perf(model): replace O(n²) string concat with O(n) fragment join in stream accumulation (#2158)
27b6a0d qbc committed 3 months ago
fix(model): reuse openai.AsyncClient across calls instead of new per call (#2063)
cba9d48 dongfeng3692 committed 3 months ago
feat(workspace): support apple container as workspace backend (#2068)
2ba25bb DiegoCluv7 committed 3 months ago
feat(webui): refactor chat pages with shadcn and prepare for npm release (#2171)
8b0b6e6 DavdGao committed 3 months ago
feat(moonshot): add Kimi K3 model support in MoonshotChatModel class (#2141)
999f64d qbc committed 4 months ago
chore(version): bump version to 2.0.5 and reorganize optional dependencies (#2157)
07f73ff DavdGao committed 4 months ago
feat(tool): add PowerShell support for Windows workspaces (#2132)
798bc18 qiuC123 committed 4 months ago
feat(agent): support structured output within the agent class (#2150)
77318e0 DavdGao committed 4 months ago
fix(anthropic): preserve redacted_thinking blocks in message round-trip (#2139)
f5f9ca6 qbc committed 4 months ago
feat(agent): inject runtime state awareness into conversation context (#2134)
29792cd DavdGao committed 4 months ago
feat(rag): add elasticsearch vector store backend (#2129)
5c69607 ouyangwulin committed 4 months ago
refactor(webui): refactor the text input component in web ui (#2102)
aa8123e Ziyang Guo committed 4 months ago
fix(agent): continue the agent loop after thinking-only responses (#2120)
96290e0 March7 committed 4 months ago
fix(permission): unify per-mode evaluation and propagate batch confirmation exemptions (#2117)
30ca3ef DavdGao committed 4 months ago
perf(prompt): improve instructions for workspace, context compression and the CreateTask tool (#2111)
614085e DavdGao committed 4 months ago
fix(tool): reject mutating find commands as read-only (#2004)
7295c98 VectorPeak committed 4 months ago
fix(agent): preserve multi-tool pairs during context compression (#2093)
2d5ebe1 qiuC123 committed 4 months ago
fix(mem0): add seperate LLM instance in mem0 example (#2078)
c359e1e Osier-Yi committed 4 months ago
fix(webui): scroll newly loaded sessions to bottom (#2100)
bdc65ac Cong Pendy committed 4 months ago
fix(app): use cursor-based pagination for list_messages (#2081)
0745ea5 DavdGao committed 4 months ago
fix(model): preserve OpenAI Responses reasoning history replay (#2071)
9254d49 qbc committed 4 months ago