AngelX v0.1.3: Open-Source Terminal Harness for Coding and Research Agents
tokenbender · x · 2026-09-22
Developer FrostForger released AngelX (v0.1.3), an open-source terminal harness for coding and research agents, calling it a first-order priority project since Aider. The demo video uses PrimeIntellect Evals as the benchmark environment.
Key features:
- Multi-panel TUI with configurable models, thinking levels, agent teams and agent graphs
- Repo tools: file search, symbol inspection, definition following, diff review
- Hashline editing that checks file content before applying anchored changes
- codemode: run tool calls, loops and filters locally in JavaScript
- Long-session context management: compaction, deduplication and context aging
- Atlas project memory with source-linked knowledge reuse
- Persistent goals, headless runs with recorded acceptance evidence
- Measured benchmarks with paired samples and verifier-based review campaigns
- One-command Linux install, built in Rust with ratatui
More from coding & agent
- Claude Code's fullscreen /diff now shows a live-updating side panel of every changed file — EricBuess · 2026-09-22
- Astra users burn quota from 100% to 0% in hours, and resets clear the timer — jdjohnson · 2026-09-22
- Agent Memory Challenge 2026 Cycle 2 opens with $22K prize pool and 150-task coding track — omarsar0 · 2026-09-22
- dotey shares doc-driven multi-agent coding workflow: Fable writes spec, Opus executes — dotey · 2026-09-22
- One LLM call decides what to remember: building fast, cheap agent memory on Jev — gdechichi · 2026-09-22
- 8 open-source agent tools: computer-use, browser control, memory and more — Aiden_Tech_Ai · 2026-09-22