# truefoundry/trueforge

> Open-source agent harness — the runtime layer that turns an LLM into a working agent: model call loop, MCP tools, skills, sandboxing, approvals, and session state. Exposed as a chat UI, HTTP API with TypeScript SDK, and embeddable UI SDK.

- Magnitude: 1.2 out of 10 — Steady
- Stars: 6,395 total · +1 star measured 2026-10-29, 00:11–05:49 UTC, ≈ 6 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: TypeScript · License: MIT · Created: 2026-07-23 · Last push: 2026-10-29
- GitHub: https://github.com/truefoundry/trueforge · Homepage: https://trueforge.dev · Page: https://gitnova.dev/en/r/truefoundry/trueforge

## Useful for

- Run a local agent via npx with SQLite and no extra infrastructure
- Connect MCP servers with OAuth and build a reusable agent from model and skill catalogs
- Embed the agent UI into your app via @truefoundry/trueforge-ui

## Why it’s here

- Star-counter measurements on 2026-10-29 (UTC), 00:11–05:49: 6394 → 6395 stars (+1). This is the change over that interval.
- Estimated end-of-day forecast: about +6 stars, using observed gains and the previous day.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 547
- Issues and pull requests: 1,195
- Watchers: 19
- Average over the last week: 10 per day
- Usual pace: 20 per day
- Stars in the last hour (measured): 0
- Latest release: @truefoundry/trueforge-ui@0.182.0-rc.1 (2026-10-29)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-30 … 2026-10-29: 16, 10, 8, 8, 15, 9, 10, 10, 6, 17, 18, 40, 30, 37, 12, 8, 18, 25, 15, 17, 13, 22, 11, 8, 11, 21, 12, 6, 7, 1

## Magnitude by day, last 14 days

10-16 1.6, 10-17 2.1, 10-18 2.1, 10-19 1.8, 10-20 1.7, 10-21 1.8, 10-22 1.9, 10-23 1.5, 10-24 1.3, 10-25 1.9, 10-26 2.1, 10-27 1.9, 10-28 1.5, 10-29 1.3

## More in this category

1. **HKUDS/DeepTutor** — 8.8 · Breakout · AI agents · Python · +521 stars measured 2026-10-29, 00:02–05:41 UTC, ≈ 1,996 by evening
   A lifelong personalized AI tutor with long-term memory: builds learning paths, reads documents and books, and runs practice and assessments via a multi-agent system and RAG.
   Full card: https://gitnova.dev/en/r/HKUDS/DeepTutor.md
2. **elayadesign/ai-design-skills** — 7.9 · Breakout · AI agents · +284 stars measured 2026-10-29, 00:02–05:41 UTC, ≈ 1,293 by evening
   A collection of markdown-based design skills for AI coding tools like Claude Code, Cursor, Codex and Windsurf, covering landing page design and turning static designs into animated showcases.
   Full card: https://gitnova.dev/en/r/elayadesign/ai-design-skills.md
3. **pbakaus/impeccable** — 7.7 · Breakout · AI agents · Rust · +704 stars measured 2026-10-29, 00:02–05:41 UTC, ≈ 2,588 by evening
   A set of commands and detector rules for AI coding agents that helps them produce better frontend design instead of generic templates. Installs as a skill into Claude Code, Cursor, Codex and other harnesses.
   Full card: https://gitnova.dev/en/r/pbakaus/impeccable.md
4. **anonnerdfrenzy/survival-llm** — 7.7 · Early signal · AI agents · Python · +60 stars measured 2026-10-29, 00:02–05:41 UTC, ≈ 350 by evening
   A local offline LLM assistant with a library of ~1.5M survival, medical and how-to articles; every answer cites the exact source passage.
   Full card: https://gitnova.dev/en/r/anonnerdfrenzy/survival-llm.md
5. **unclebob/ub-mode** — 7.6 · Breakout · AI agents · +236 stars measured 2026-10-29, 00:02–05:41 UTC, ≈ 1,087 by evening
   An agent skill that enforces disciplined software engineering practices when writing or changing code: TDD, root-cause fixes, behavior testing, and quality gates via mutation testing. Installed as SKILL.md into the agent's skills directory.
   Full card: https://gitnova.dev/en/r/unclebob/ub-mode.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-29 05:52 UTC, updated every 30 minutes.