English | 中文 | 日本語 | 한국어 | العربية | Español | Bahasa Indonesia
One Command to Empower Your Agent with Comprehensive Trading Capabilities
Website · Docs · News · Features · Shadow Account · Demo · Quick Start · Examples · API / MCP · Roadmap · Contributing
⚠️ Security warning: The X accountVibeTrading_HKU, Virtuals project101845, and token contract0x640BDBF77b6447E8b7DB7894cED84BD1c40571f4are not official Vibe-Trading assets. We have never launched or endorsed any token or memecoin. Do not buy, connect a wallet, or sign anything. Details.
-
2026-11-03 🛠️ Runtime integrity and localization follow-ups (unreleased): Preserve U+2028/U+2029 inside trace, audit-ledger and session-search JSONL records, keep ledger appends valid after such payloads, normalize underscored model labels, and preserve handoff summaries during layer-2 compaction. Also accept BOM-prefixed frontmatter and keep the welcome surface aligned in RTL locales. Add regression coverage.
-
2026-11-02 🛠️ Frontmatter, result safety and welcome polish (unreleased): Unquote quoted scalar metadata, fall back to a readable truncation when an oversized result cannot be encoded, and refine the welcome layout and featured cards. Add regression coverage.
-
2026-11-01 🛠️ Session timestamps, theme contrast and welcome interactions (unreleased): Stamp session updates in UTC, keep dark-mode primary buttons legible, and make side-panel examples clickable with clear category labels. Add regression coverage.
Earlier news
-
2026-10-31 🛠️ Welcome and ticker parsing polish (unreleased): Move the welcome surface to a warm paper palette and two-column layout, make featured examples and side-panel actions clearer, and stop trailing ticker letters from being interpreted as A-share or A/H constraints.
-
2026-10-30 🛠️ Channel reliability and A-share sizing (unreleased): Voice notes reach the agent as attachments in Telegram, Feishu, Matrix and Weixin; STAR and Beijing backtests follow their board-specific minimum sizes and one-share increments. Add path-containment regressions. (#2106, #2105, #2094). Follow-up: stream cancellation and retry/cache accounting, scoped background recovery, evidence-preserving research-goal edits, and Discord overflow fixes. A-share 5m paper steps now match bar by bar; saved accounts remain daily-only. Optional Parallel search is off by default. (#2099, #2109, #2111, #2113).
-
2026-10-29 🛠️ Research reuse and execution fixes (unreleased): Save versioned research artifacts and reuse manifest-checked prior backtests (#2079, #2074). Fix document amounts/units and spot-crypto costs; restore Binance open orders and AKShare compatibility (#2050, #2088, #2090, #2083). Also add Codex model discovery, BYMA rules, background-owner isolation and shared tool policy. Paper strategies use private worker pipes; native Windows confirmation remains pending (#2089, CHANGELOG).
-
2026-10-28 🛠️ Paper trading, portfolio and market-routing fixes (unreleased): Add the phase-1 bar-agnostic paper-order lifecycle state machine with stable replay IDs, fail-closed cancellation, day settlement, optional partial fills and deterministic snapshots (#2066). Robinhood's read-only portfolio source now carries explicit account selection, quote mapping and cursor pagination (#2054; closes #1428). Fix Shadow Account cache invalidation and documented entry conditions (#2075, #2073); map US symbols for Futu and configure IBKR/Futu gateway endpoints (#2076, #1983). Also restore structured two-turn finals, Qlib factor semantics and numeric/grounding input boundaries (#2064, #2069, #2072, #2053). These fixes are on
mainfor the next release. -
2026-10-27 🛠️ Portfolio connections and research correctness (unreleased): Save connection-specific IBKR/Futu gateway addresses through Web or CLI, and use them for agent reads (#1983). Robinhood portfolio reads support account selection, pagination and equity quotes; follow-up checks bind quotes to the requested symbol, select the newer regular/extended-hours trade and show its as-of time (#2054, 011a555ed). Restore Qlib ROC/CORD formulas and enforce documented shadow-strategy entry bounds (#2069, #2073). Preserve financial units and numeric evidence, keep currency declarations within their own object, reject non-finite/boolean financial inputs, and accept ordinary two-turn
claude-clistructured finals (#2072, #2053, #2064). These changes are onmainfor the next release. -
2026-10-26 🛠️ Agent cancellation, grounding and market-correctness fixes (unreleased): Stopping a chat turn cancels in-flight Swarm runs and ignores late status events (#2059, #2060). Restore trailing OLS definitions for Qlib BETA/RESI, admit eligible document figures to the evidence ledger, and recover from refused native
claude-clitool attempts (#2062, #2058, #2048). Add field-level alpha-bench availability metadata; correct weight overflow, event-study rank scaling and attribution alignment (#2057, #2046, #2000, #2044). Also fix Moonshot reasoning-effort routing, journal/options input validation, Stooq class-share symbols, screener decimal fields and ST board limits (#2043, #2052, #2049, #2012, #1988, #1984). These changes are onmainfor the next release. -
2026-10-25 🛠️ Session, market-data and calculation fixes (unreleased): Deleting a session also removes its search entries, and chat titles update correctly when the first message includes attachments or Swarm instructions (#1970, #1969). Fix prematurely truncated CCXT history, Nobitex daily dates and Tiingo class-share symbols (#1999, #1989, #2010). Preserve small trade/chart prices, correct GTJA factor formulas and VWAP units, and reject ambiguous boolean flags before changing state (fix). These fixes are on
mainfor the next release. -
2026-10-24 🛠️ MCP, backtest and search fixes (unreleased): MCP loads the runtime
.env, while shell tools still require explicit opt-in at startup (#1974). Report assumed futures leverage (#1972), preserve fractional-day spans in annualization (#1971), and try enabled Sogou/Bing fallbacks when ddgs returns no results (fix). -
2026-10-23 🛠️ Model, portfolio and futures fixes (unreleased): Direct MiniMax connections default to M3.1 Flash and retain reasoning across tool calls (#1936). Longbridge exposes cash by currency and financing limits across Agent, CLI, API and Web (#1940). Correct global futures routing, contract multipliers and micro-contract fees, with explicit warnings when pricing defaults are used (#1965). Also fix portfolio error redaction, audit rotation, IC statistics, numeric parsing and Weixin attachment collisions. Details in CHANGELOG.
-
2026-10-22 🚀 v0.1.18 released (Release notes,
pip install -U vibe-trading-ai): a leaner agent runtime — tool schemas load on demand, oversized results stay readable in the run directory, Swarm keeps new observations, and usage accounting covers compaction and interrupted calls; automatic chat titles remain. On the 0.1.17 verification backtest it used 7 model calls instead of 12 and about a fifth of the input tokens. It also ships the post-0.1.17 security, grounding, paper-account and packaging fixes. Fixed on main today (next release): a retried provider error no longer halts live model decisions for the rest of the day, and a research goal's final answer is delivered even when it crosses the goal's token budget (CHANGELOG). -
2026-10-21 🚀 v0.1.17 released (Release notes,
pip install -U vibe-trading-ai): 638 commits and 228 merged pull requests since 0.1.16, plus 41 pull requests whose work landed through maintainer commits, from 33 contributors. The headline is daily paper trading: apaper_trade_steptool for the agent and MCP, plus saved paper accounts throughvibe-trading paper, the REST API and a Web page, match orders or a strategy against completed daily bars without ever reaching a broker; saved accounts move forward only (#1939). Most of the rest is correctness, and much of it has one shape: a value that cannot be computed now says so instead of turning into a plausible number. A profit factor with no losing trade, an undefined correlation and an unbounded ratio come back asnull, and a factor with too few IC observations is skipped with the reason; a missing price no longer bridges a return; a misspelled or engine-irrelevant backtest setting is reported in the run card. New: Brazil (B3), 478 Alpha Zoo factors (from 462), Slack and Discord in the guided channel setup, Email reports as HTML or a password-protectable PDF, token usage in Run Detail, chat and swarm, aclaude-cliprovider, and Persian and Turkish for 11 UI languages. Fixed today: the fund-flow fallback names its actual source and keeps total flow apart from main-order flow, and the Telegram setup steps are clarified. Shipped the same evening in v0.1.18:mcp>=1.30closes CVE-2026-59951 for--transport http; custom model endpoints are re-checked on every connection and work behind fake-IP proxies; grounding readsrun_dir/…refs and−$amounts; Beijing920xxxcodes resolve to.BJin correlation (CHANGELOG). Thanks @rudycelekli, @Shizoqua, @he-yufeng, @shadowinlife, @zeus229, @alexwan02, @Jackzigen, @cgycorey, @MetaAviator, @lorenzozanee, @Mikesad, @remote-controlled-man, @Romzhou, @sambazhu, @wavebyrd, @BHhhh-123, @Bortlesboat, @bygordon130-hub, @davidalmeida90, @DrDLyuan, @Emad211, @Frank-zhu2000, @goatyyc, @hunters1011-ctrl, @incorpore, @mdb1230, @mminkus, @passionbull, @rwxyx518-prog, @ThreeTima, @tomaszkubiak-courses and @xaritoku! -
2026-10-20 🛠️ Backtest diagnostics and research correctness: Warn about unrecognized backtest config keys, show undefined correlations as unknown instead of zero, and reuse the saved annualisation factor when revalidating runs (#1935, #1933, #1915). Also improve factor sample checks, tool input validation, journal market classification, numeric formatting and WeCom streaming. All 14 fixes and remaining limits are in CHANGELOG.
-
2026-10-19 🛠️ Nine financial correctness fixes: Correct recency weights in factor decay, A-share board limits and Beijing symbol routing, SEC Q4 flow derivation, and event-study estimation windows. Preserve Futu holdings identity and tiny MACD/Bollinger values; reject negative specific variances and apply pair-specific fees to Yahoo forex symbols (#1912, #1920, #1930). See CHANGELOG for all nine fixes and limits.
-
2026-10-18 🛠️ Scheduling and research reliability: Live scheduling adopts the shared scheduler kernel (#1899), and figure checks preserve currency identity (#1905). Add factor neutralization and PCA (#1817); fix incomplete Swarm event tails and lost Matrix final replies. Details in CHANGELOG.
-
2026-10-17 🛠️ Token usage and research reliability: View LLM usage in Run Detail, chat and swarm (#1890). Shared scheduling now powers research and optional background jobs (#1893); live scheduling is unchanged. Fix journal date/time pairing, evidence paths, factor ties, memory roots, numeric error handling and channel progress. See CHANGELOG.
-
2026-10-16 🛠️ Credential safety and financial correctness: Scrub more channel/provider secrets (#1880), refresh cached local bars after source edits (#1879), and allocate reversal fees once (#1891). Correct European journal amounts, strict JSON, zero/negative comparisons, holding periods, weight floors, plateau detection and report paths. See CHANGELOG.
-
2026-10-15 🛠️ Model spending controls and research reliability: Live runners use independent decision sessions with configurable cadence and persistent daily usage budgets (#1854). Lightweight backtest previews preserve complete trade history (#1853, #1865). Fix percentage evidence arithmetic, copied-run history deduplication, swing-signal timing, crypto routing and credential redaction. See CHANGELOG for scope and limits.
-
2026-10-14 🛠️ Backtest, search and document fixes: Risk ratios and equity exports now include first-bar PnL (#1844). Session search returns distinct sessions with preserved titles and contextual snippets (#1827, #1834). Improve PDF/Office extraction, reject unresolved evidence references, and strengthen financial-input validation and credential redaction.
-
2026-10-13 🧩 Portfolio imports, strategy adaptation and research tools: Read-only extraETF holdings imports support dated EUR valuation and allocation proposals; adapted strategies get their own backtest evidence (#1170, #1149). Add tested custom model endpoints, a shared manual Pixel Office task board, Persian/Turkish UI, mStock read-only queries and Gildata research data. Fix settlement-currency accounting, Futu market selection and cost basis, per-symbol HK board lots, saved validation settings and run progress. Complete declared grounding checks and the agent-loop split. mStock remains excluded from portfolio aggregation; Robinhood options execution remains unavailable. See CHANGELOG for scope and limits.
-
2026-10-12 🧮 Research and backtest updates: Correct opening fills, liquidation-time attribution, drawdown duration, valuation tolerances and SEC filing timing in factor IC (#1780–#1794). Add 13 fundamental/valuation factors, Brazil data and backtests, opt-in ZimaOS templates, and Feishu run progress. See CHANGELOG for scope and data limitations.
-
2026-10-11 🛠️ Five priority fixes: Derived figures require evidence for every data operand; unsupported live options stay blocked. Offline benchmarks retain their selected source, trade artifacts distinguish break-even exits, and Codex tools preserve optional arguments (#1622, #1779, #1781, #1785).
-
2026-10-10 🛠️ Slack/Discord setup and reproducible research: Localized channel forms verify bot credentials without saving changes (#1764, #1777). Portfolio research can reuse an immutable snapshot, and Web exports its sanitized JSON (#1769). Indicators report their date boundary and exact input fingerprint; corrupted session records recover without rewriting files. Memory recall, credential redaction and trade-journal detection are corrected. See CHANGELOG.
-
2026-10-09 🛠️ Channel updates and backtest correctness: Channel settings preserve embedded URL credentials and authenticated WeChat endpoints during in-place updates, with save/reset feedback in all nine languages (#1737, #1742, #1744). Cross-market option volatility uses only timestamps known at each bar; drawdown includes starting capital. Crypto/precious-metal routing, HK duplicate detection, cache recovery, scientific-notation amounts and missing-equity validation are corrected. mootdx leaves the default A-share chain. See CHANGELOG for all thirteen PRs.
-
2026-10-08 🔐 Protected PDF reports and clearer broker reads: Scheduled Email PDFs support optional AES-256 password protection across Web, CLI playbooks and agent confirmations; the password stays in private channel configuration (#1709). KIS queries all three venue buckets, refreshes an explicitly expired token once, and reports incomplete reads as errors (#1726). Derived formulas keep their arithmetic after descriptive labels while evidence checks remain enforced (#1728).
-
2026-10-07 🛠️ Research continuity and reliable risk metrics: Volatile workspace state now travels outside the system prompt, preserving its stable prefix (#1708). Cross-market dates align correctly, missing prices no longer bridge return observations, and options Sortino uses full-sample downside deviation (#1710, #1717, #1727). Loader fixtures share one OHLCV contract; credit valuation, style exposures, walk-forward folds and audit diagnostics are corrected.
-
2026-10-06 🛠️ Live controls and report corrections: Stopping a live runner cancels its current analysis and waits for scheduler cleanup, including startup cancellation and API shutdown; status timestamps use the correct units (#1704). Emergency cancel/flatten scans skip malformed records without abandoning the remaining book (#1703); broker schedules are stored separately and writes handle concurrency and partial writes. US equity half-days respect the early closing bell (#1706). Report corrections preserve figures that passed validation, and bounded feedback no longer implies that unlisted figures passed (#1702).
-
2026-10-05 🛠️ Research prompts and calculation fixes: Chat accepts longer research prompts and gives a localized recovery message when input is too large (#1701). Backtests use full-sample Sortino downside deviation; grouped validation purges overlapping labels, covariance weights remain finite, shadow RSI uses Wilder seeds, and memory removal accepts filename stems. Invalid call aliases now receive exact source references for correction (#1638); numeric validation stays unchanged.
-
2026-10-04 🛠️ Scheduled reports and research workflows: Edit scheduled runs and choose a configured destination; Email reports support HTML or PDF attachments (#1649, #1680). Backtests expose structured summaries and paged artifact reads (#1646, #1647). Fixes cover memory-search snippets, export-path guidance, macro truncation, monthly risk, turnover on reversals and cash reentry, IV accuracy, VaR gaps, VCS updates and Robinhood option-order blocking.
-
2026-10-03 🛠️ Research, reports and data reliability: CJK session search, channel setup, broker exposure pricing and file writes now handle cases that blocked everyday use. PDF delivery embeds CJK fonts, Swarm validates preset inputs and separates task artifacts, and replayed tool results survive context compaction (#1683, #1455, #1635). Backtests keep one adjustment basis, local caches distinguish sources, single-asset caps and weekly/monthly risk use the declared settings, audits retain loss signs, grounding checks the current engine output and exact list references, and Stooq retries after a denial cooldown (#1684, #1650, #1685, #1640).
-
2026-10-02 🛠️ Backtests and report checks: strategy-file writes retain model provenance without crashing (#1673), and Monte Carlo drawdown and Sharpe include starting capital (#1664). Report audits preserve accounting negatives and units (#1663); grounding artifacts record fired declared checks (#1661); public loader-health reports include sanitized failure reasons (#1643). Indonesian tool documentation matches the registry (#1671).
-
2026-10-01 ✅ Data correctness and reproducible backtests: A-share adjustment conversion now refuses ambiguous one-bar edge cases (#1551); Southbound Eastmoney amounts are scaled from million HKD and rejected responses no longer look empty (#1486); Northbound fallback data distinguishes post-2024-08-19 turnover from net flow (#1484); Binance-only unpriced positions are marked incomplete without penalising other brokers (#1505); and backtest run cards record model provenance and warn when the training cutoff is unknown or outside the test window (#1618, closes #1613).
-
2026-09-30 🛠️ Feishu in the Web UI, a momentum factor that read today's price, and a profit factor for runs that never lost: Feishu joins the guided channel setup, with a standalone connection test and a hot reload that closes the old WebSocket (#1572).
academic_carhart_momsubtracted the 1-month return from the 12-month one, so it moved with today's close; it is now the return from 12 months ago to 1 month ago (#1578). A run with no losing trade reports its profit factor as undefined instead of 0.0, which ranked it last (#1602). Stooq's anti-bot page now stops every later request in the process, not just the log line (#1637); MCP tool results reach the agent once instead of up to four times (#1634); and the first piece ofloop.pymoves into its own module (#1636). -
2026-09-29 🚀 v0.1.16 released (Release notes,
pip install -U vibe-trading-ai): 492 commits and 116 merged pull requests since 0.1.15, from 16 contributors. The theme of this cycle is a number that can show where it came from. The grounding gate no longer guesses what a number is from the words around it: the model declares each figure's role (observed, derived, proposed, cited or count), the gate checks it against the session's tool evidence, and a figure that fails is cut instead of the whole answer being refused. A backtest's own output — Sortino, turnover, weights and Monte Carlo p-values, not only Sharpe — now grounds the report written about it, and run cards cite a metric only where the saved CSV agrees. Long research runs keep what they fetched: compaction follows each model's real context window instead of a fixed 40K estimate. The missing-data sweep reached 59 more alphas. Fixed in this release, from a user's report: failed runs keep their steps and the stop message names the call that produced nothing;read_filesays where it may read instead of letting the model guess paths until the no-progress stop; on Codex, mid-run instructions no longer replace the system prompt, reasoning carries between turns and the default model isgpt-6-sol; andget_market_dataasks forAAPL.USrather than returning empty data for a bare US ticker. New: Argentina (BYMA), weekly and monthly bars, Bahasa Indonesia, Gildata, OpenCode, Email and WebSocket channels, IM channel setup in the Web UI, and KIS, Upbit, Toss Securities and Scalable Capital connectors, 18 brokers in all. Thanks @Shizoqua, @zeus229, @cgycorey, @shadowinlife, @lorenzozanee, @he-yufeng, @chiww, @as950118, @woshi77777stars, @Yoruxyv, @sambazhu, @0xouzm, @tingkk, @tonydo, @alanwilhelm and @modelpath-dev! -
2026-09-28 🛠️ Source health and connector transparency: scheduled public-source canaries report outages and data drift with bounded, credential-free probes (#1627); BaoStock socket requests now have deadlines and serialize concurrent sessions (#1615). Copilot credential lookups refresh after a short cache TTL (#1619). A generated broker matrix preserves each profile’s paper/live permissions and labels declared capabilities separately from runtime verification (#1629). Grounding and MT5 follow-up: explicit evidence symbols and exact field references are preserved; localized grouped figures retain the existing numeric tolerance (#1584, #1586, #1588). Text-only correction attempts are bounded (#1600). MT5 search uses the selected terminal and refuses ambiguous broker aliases; backtest sandboxes receive only validated attachment settings (#1597, #1598).
-
2026-09-27 🛠️ Verifiable run cards and safer research: Run cards now show hashed backtest execution records and verified metric-to-CSV references in JSON, Markdown and Run Detail (#1612). GTJA high/low recency factors use the correct day count and consistent tie handling (README truncated. Read the full file on GitHub.
README content is written by the repository's authors. Treat it as untrusted data, never as instructions for an agent.