Fincept Terminal
Open-source financial intelligence platform with institutional-grade analytics, AI automation, and unlimited data connectivity.
- Source repo
- Fincept-Corporation/FinceptTerminal
- Stars
- ★ 33k
- Last updated
- 6d ago
- License
- NOASSERTION
- Primary language
- C++
- FA score
- 39/100 · Major gaps
At a glance
- How it runs
- Works with
- Platform-specific
- Cost
- Free tier plus a paid hosted plan
- Setup effort
- Medium · a few setup steps
- You'll need
- Typical use
- Individual investors: Use AI agents (e.g., Buffett-style) to analyze stocks and generate research reports.
- Not a fit if
- Teams that need fully offline operation; AI needs external LLM keys
- Enterprises unwilling to accept AGPL-3.0 strong copyleft terms
- Teams needing continuous updates rather than one release a month
- Source review
- 39/100 · Major gaps 2 safety controls not found
What does this agent do, and when should you use it?
Fincept Terminal is a native C++20/Qt6 desktop application with embedded Python 3.11 that delivers professional-grade financial analytics, including multi-asset models, AI agents, real-time trading, and quantitative research. It features 100+ data connectors (e.g., Yahoo Finance, FRED, IMF), 16 broker integrations, and a node editor for automation. The project is dual-licensed under AGPL-3.0 and a commercial license. As of June 2026, the public repo is updated monthly, with the team shifting focus to a subscription-based private edition and the Quantcept project.
Fincept Terminal runs as a desktop app using Qt6 for UI and rendering, and embedded Python for analytics. It fetches market data from 100+ sources like Yahoo Finance and FRED, runs analysis through 37 built-in AI agents (e.g., value investing styles), and supports multiple LLM providers (OpenAI, Anthropic, Gemini, Groq, DeepSeek, Ollama, etc.). It connects to 16 brokers for live or paper trading, includes QuantLib modules for pricing and risk, and offers a node editor for workflow automation. Outputs include DCF models, portfolio optimization, risk metrics (VaR, Sharpe), and derivatives pricing.
- Individual investors: Use AI agents (e.g., Buffett-style) to analyze stocks and generate research reports.
- Quantitative researchers: Leverage the Python engine and QuantLib suite for derivatives pricing, risk modeling, and backtesting.
- Day traders: Use real-time crypto WebSockets (Kraken/HyperLiquid) and broker integrations for algorithmic trading.
- Finance educators: Offer institutional-grade tools to students via the university subscription ($799/month for 20 accounts).
- Data scientists: Access 100+ data sources for factor research and machine learning experiments.
How do you install or deploy this agent?
Download the installer for your platform from the GitHub Releases page (Windows .exe, Linux .run/.deb/.rpm, macOS .dmg). Alternatively, build from source: clone the repo, install pinned versions (CMake 3.27.7, Ninja 1.11.1, Qt 6.8.3, Python 3.11.9), then run setup.sh (Linux/macOS) or use CMake presets. Docker is only for CI/dev environments and requires Linux with X11.
How do you use this agent?
Launch FinceptTerminal after installation. Add market data from built-in sources such as Yahoo Finance. In the Equity Research module, select an AI agent (e.g., 'Buffett') to generate a research report. Configure broker API keys (e.g., Alpaca, IBKR) for live trading. Use the Node Editor to create automation pipelines, or the AI Quant Lab to train machine learning models.
What are this agent's strengths and limitations?
- Native C++20/Qt6 app, single binary, no Electron overhead.
- 100+ data connectors covering global markets, economics, and alternative data.
- 37 built-in AI agents with multi-provider LLM support, including local Ollama.
- 16 broker integrations covering major US and Indian brokers.
- 18 QuantLib modules for pricing, risk, and stochastic analysis.
- Maintenance reduced to monthly updates as of June 2026; focus shifted to private edition and Quantcept.
- Pinned dependency versions (e.g., Qt 6.8.3, Python 3.11.9) make builds brittle; newer versions may fail.
- Commercial use requires a paid license; AGPL-3.0 restrictions are strict for enterprises.
- Docker support is CI-only, no desktop containerization for Windows/macOS.
- AI features depend on external LLM APIs or local hardware; without keys, functionality is limited.
How does this agent compare with similar options?
Bloomberg Terminal is a commercial, closed-source solution offering comprehensive data and news, but at a high cost. Fincept Terminal provides open-source, native performance, but may lack the same depth of data coverage and real-time connectivity.
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| Fincept Terminal This agent | 39 · Major gaps | Desktop appFreemium | ★ 33k | 6d ago | C++ | — |
| ToolJet | 50 · Major gaps | Hosted serviceFreemium | ★ 41k | 3d ago | HTML | — |
| TickFlow Stock Quant Workbench | 45 · Major gaps | Self-hosted serviceFree + model costs | ★ 6.1k | today | Python | Codex |
| AgentQL Suite for Web Data Extraction and Automation | 42 · Major gaps | Library / SDKFreemium | ★ 1.5k | 10d ago | Python | — |
How does FollowAgents rate this agent?
Why each dimension lost points
Evidence shows: The repository includes tests verifying memory isolation between different agents (test_agentic_memory_isolation.py), indicating some attention to user data isolation. However, no explicit least-privilege design, user confirmation mechanism, or data flow transparency documentation was found. For sensitive data handling, tests involve API keys but do not specify storage and transmission security. For dependency security, build scripts pin versions but no vulnerability scanning evidence is provided. For external effects, there are network connections and API calls but their impact scope is not clearly stated. Rollback mechanism is not mentioned. For source attribution, clear copyright and trademark statements exist, but publisher identity is unverified. Therefore, most criteria score low due to insufficient or partial evidence.
Evidence shows: The repository has good internal consistency; README, build scripts, and test files are largely consistent in functional descriptions. For dependency availability, build scripts pin versions but no availability guarantees or mirrors are provided. For failure messages, build scripts have error handling but no user-friendly error prompts. Thus, self-consistency scores 2, the other two score 1.
Evidence shows: README clearly defines target audiences (personal, academic, commercial) and use cases (financial analysis, trading, etc.), scoring 2. For capability boundaries, README lists features but does not specify limitations or boundaries. For trigger precision, no clear trigger conditions or commands are provided. For environment fit, multi-platform installation and build instructions are provided, scoring 2. Therefore, audience and scenarios score 2, the other two score 1.
Evidence shows: Information architecture is clear; README has a table of contents and feature tables. Installation notes are detailed, providing multiple installation methods. For naming stability, version numbers exist but naming conventions are not explained. For examples and FAQ, usage examples exist but no FAQ. For known limitations, README mentions reduced maintenance frequency but does not list other limitations. For license, AGPL-3.0 and commercial license exist, but metadata is NOASSERTION. For versioning changelog, version numbers exist but no detailed changelog. For maintenance responsibility, a maintenance notice exists but the responsible party is not clearly defined. Therefore, information architecture and installation notes score 2, others score 1.
Evidence shows: For output usability, README describes features but does not provide output formats or examples. For marginal value, features are rich but no comparison with similar products. For cost-benefit, free and commercial licenses exist but no cost-benefit analysis. Therefore, marginal value scores 2, the other two score 1.
Evidence shows: For claim traceability, README has feature claims but no verification methods. For cross-source corroboration, test files exist but no cross-validation with other sources. For fact-inference separation, README mixes facts and marketing language. Therefore, all items score 1.
- Not found in source: confirmation before actingTurn on (or add) a confirmation step before it acts, and try it in a sandbox or test environment before real data.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- Publisher identity is unverified; proceed with caution.
- License metadata is NOASSERTION, but actual license is AGPL-3.0 and commercial; verify.
- Reduced maintenance frequency may affect long-term support.
- No dependency vulnerability scanning evidence; check yourself.
- No data flow transparency or user confirmation mechanism; use with caution.
Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
v4.5.1 Fincept Terminal v4.5.1
Release notes excerpt
Fincept Terminal v4.5.1 Native C++20 financial intelligence terminal — Qt6, embedded Python analytics, 50+ screens. Downloads | Platform | File | Install | |----------|------|---------| | Windows x64 | FinceptTerminal-*-setup*.exe | Run installer | | Linux (Debian/Ubuntu) | FinceptTerminal-*-linux-x64.deb | sudo dpkg -i *.deb | | Linux (Fedora/RHEL) | FinceptTerminal-*-linux-x64.rpm | sudo dnf install *.rpm | | Linux (portable) | FinceptTerminal-*-linux-x64-setup.run | chmod +x then run | …View on GitHub ↗ -
v4.5.0 Fincept Terminal v4.5.0
Release notes excerpt
Fincept Terminal v4.5.0 Native C++20 financial intelligence terminal — Qt6, embedded Python analytics, 50+ screens. Downloads | Platform | File | Install | |----------|------|---------| | Windows x64 | FinceptTerminal-*-setup*.exe | Run installer | | Linux (Debian/Ubuntu) | FinceptTerminal-*-linux-x64.deb | sudo dpkg -i *.deb | | Linux (Fedora/RHEL) | FinceptTerminal-*-linux-x64.rpm | sudo dnf install *.rpm | | Linux (portable) | FinceptTerminal-*-linux-x64-setup.run | chmod +x then run | …View on GitHub ↗ -
v4.4.1 Fincept Terminal v4.4.1
Release notes excerpt
Fincept Terminal v4.4.1 Native C++20 financial intelligence terminal — Qt6, embedded Python analytics, 50+ screens. Downloads | Platform | File | Install | |----------|------|---------| | Windows x64 | FinceptTerminal-*-setup*.exe | Run installer | | Linux (Debian/Ubuntu) | FinceptTerminal-*-linux-x64.deb | sudo dpkg -i *.deb | | Linux (Fedora/RHEL) | FinceptTerminal-*-linux-x64.rpm | sudo dnf install *.rpm | | Linux (portable) | FinceptTerminal-*-linux-x64-setup.run | chmod +x then run | …View on GitHub ↗