temm1e

Name: temm1e
Rating: 64 (1 reviews)
Author: temm1e-labs

temm1e-labs/temm1e

TEMM1E is an autonomous AI agent runtime built in Rust designed to run persistently across multiple platforms with advanced memory, self-learning, and verification capabilities.

490 104No licenseUpdated 2026-07-04

Good

View on GitHub Open source file

Overview

TEMM1E is an advanced, production-grade autonomous agent runtime implemented in Rust that operates as a persistent service across various interfaces like Telegram, Discord, and a local TUI. It features a sophisticated cognitive architecture comprising 14 self-learning layers, a self-growing code mechanism (Cambium), local model fine-tuning (Eigen-Tune), and a verifiable contract ledger (Witness) to ensure reliable and verifiable agent execution without self-marking fabrication.

Capabilities

▸Full computer use and desktop automation
▸Persistent multi-platform server mode (Telegram, Discord, Slack, WhatsApp)
▸Multi-layered memory management (Lambda and Engram memories)
▸Self-growing Rust code generation and compilation (Cambium)
▸Contract-based task verification and tamper-evident ledger (Witness)
▸Local model distillation and routing (Eigen-Tune)
▸Web search and browsing integration

Best for

Running a persistent, self-updating AI assistant on local servers or cloud infrastructure, Executing complex multi-step coding, refactoring, and testing tasks with strict budget and verification controls, Automating desktop workflows using full computer use capabilities and browser automation, Managing long-term cross-task memory and continuous user preference adaptation

Works with

Claude Code

Evoa Score breakdown= Σ (score × weight)

Task usefulness20%100 → +20.0

実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析

Code quality15%95 → +14.3

実装・指示の品質。 — AIによるSKILL.md/README解析

Maintenance15%85 → +12.8

リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ

Documentation12%42 → +5.0

ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量

Security15%50 → +7.5

危険・不審な挙動が無いか。 — AIによるセキュリティレビュー

Originality10%90 → +9.0

ありふれたラッパーではない独自性。 — AIによる独自性判定

Popularity8%71 → +5.7

コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）

Compatibility5%25 → +1.3

対応AIエージェントの広さ。 — AIによる対応エージェント判定

Weighted total75.5 / 100

ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。ランキングはこのScoreのみで決まり、広告で変わりません。算出方法の詳細 →

Security considerations

The agent features high-privilege access including full computer control, shell execution, and file system modifications. Users should configure strict spending ceilings and review permissions when deploying in server mode.