Anacondahood launches: conda research + Robinhood MCP + onchain rails for AI trading agents
teoliphant · x · 2026-09-20
teoliphant launches Anacondahood, an ecosystem unifying Python research, AI agents, and trading workflows:
- Three rails: research (pinned conda env with Python 3.12/JupyterLab), broker (official Robinhood MCP for listed equities via a dedicated agentic sub-account), and chain (EVM client on Robinhood Chain for Stock Tokens, swaps, lending).
- Built-in risk: versioned risk.yml limits checked before routing — $250 max broker order, $100 max chain tx, $500 daily loss cap, human approval above $200.
- Safety: external signer keys never in env, Shift+K kill switch for both rails.
Caveat: the post includes a token contract address, so the crypto angle warrants caution.
Related event: Anacondahood Unifies Python Research and AI Trading Agents(2 posts)→
More from coding & agent
- Google's Agent Substrate detailed: AX app layer on managed agentic compute infra — rakyll · 2026-09-21
- After 15 years of better dashboards, agents can now execute finance transactions themselves — LexSokolin · 2026-09-21
- Why sandbox-as-a-service startups are booming — and whether labs will just build it themselves — dejavucoder · 2026-09-21
- KGQALLM: open-source natural-language QA over knowledge graphs with auto SPARQL generation — adnan_hashmi · 2026-09-21
- JEV, a no-text decision model claims 200x speed and 400x cost savings, with an early port of Claude Code compaction hitting 4,575 stars in five days — gaganghotra_ · 2026-09-21
- 16x Microsoft MVP rebuilds PowerShell GridView with AI, adding live search, filters, and pipeline pass-through — dfinke · 2026-09-21