TradingAgents: trading research with optional Jev screening

AgentScope builds agents around model reasoning and tool use, with context management, event streaming, memory and permission controls. JevClassifierModel integrates the Jev classifier through the TypeSafe SDK within this broader agent framework.

Planning and execution agents gather, summarize and track sources, then combine findings into a cited research report. When TYPESAFE_API_KEY is present, Jev scores passage usefulness for the research question before the LLM reads the context.

This self-hosted trading stack covers Python strategies, backtests, paper trading, live execution and monitoring. Jev evaluates order, strategy, exposure, position and budget context, returning typed choices with probabilities for the entry filter.

The self-hosted platform organizes agents, isolated workspaces and task boards across your own computers. The README lists TypeSafe's Jev as an available model that returns typed decisions with confidence rather than generated text.

This npm library and Claude Code plugin compact history by pruning tool calls and results instead of rewriting conversation text. Jev answers separate noul questions about retaining each call and result; thresholds determine whether to keep, shorten or remove the pair.

The native CLI supports an interactive shell, scripted requests and embedding, with skills, MCP servers and subagents. Jev receives review policy, context and the pending action, returning a clear or caution decision for the permission pipeline.

Instructions, tools, skills, channels and schedules live in conventional directories, making an agent project inspectable and extensible. The evaluate helper sends typed questions about supplied state through eve's model authentication, defaulting to Jev.

The platform supports developing and evaluating SRE agents against live system environments containing operational failure scenarios. Jev support is disabled by default; when enabled for Codex, it reviews diagnostic tests and submissions from evidence sent to TypeSafe.

No project description available.

🚀 Feather Wand - JMeter Agent for performance engineers w/ Codex and Claude Code integration

Agent orchestration that guides projects toward demonstrable goals.

Self-hostable managed agents harness. Author YAML manifests; Felix compiles them into governed agents with durable fibers, memory, skills, eval, approvals, and sandboxes — over OpenAI, A2A, MCP, and SSE. Fork, rewind, and steer runs. Docker, Helm, AWS, or GCP.