Neura

Neura is a Rust terminal agent for coding, debugging, provider experimentation, local model diagnostics, adaptive memory, and operational repair learning. It is designed to be hackable: the implementation is in this repository, the documentation is source-backed, and the validation scripts can detect stale inventory.

Quick install

Run the installer, reload your shell path if needed, then start Neura:

curl -fsSL https://raw.githubusercontent.com/icedmoca/neura/main/install/install.sh | bash
exec "$SHELL" -l
neura

If you already cloned the repo locally, you can run:

./install.sh
neura

Why Neura exists

Neura is built for developers who want a terminal-first coding agent that can:

• inspect and edit the same workspace you are using;
• call local tools and shell commands with visible results;
• route across multiple model providers;
• diagnose local LM Studio/OpenAI-compatible model servers;
• remember useful operational signals locally;
• learn recurring repair patterns from build, test, runtime, provider, auth, network, tooling, and context failures;
• keep its documentation synchronized with what is actually implemented.

Current capabilities

Excellent adaptive memory

Neura has a strong local memory system designed for real coding work. Its adaptive cognition layer records useful execution signals, retrieves compact prompt memory, and keeps prior operational context available without dumping entire transcripts back into every turn. On top of that, operational repair learning turns repeated build, test, provider, runtime, auth, network, tooling, and context failures into reusable repair motifs.

The result is memory that is practical rather than noisy: Neura can carry forward what mattered, surface prior fixes when similar failures recur, and keep improving its repair instincts while staying deterministic, local, and testable. This makes Neura especially good at long-running repository evolution where the agent benefits from remembering what worked, what failed, and what validation was needed.

Token savings from memory and local sidecar work

Neura is designed to save tokens by remembering the right things instead of replaying everything. Adaptive cognition keeps compact, high-signal memory; repair learning stores concise failure→fix motifs; and the optional local sidecar model can handle cheaper support work such as summaries, routing hints, critique, memory compression, and local diagnostics. That means the expensive frontier model can spend more context on the current task while Neura preserves continuity through compact local state.

In practice this helps long sessions stay efficient: less repeated explanation, less transcript bloat, fewer repeated investigations, and faster recovery when a familiar build or test failure returns. The local sidecar model is especially useful as a low-cost assistant for background understanding while the primary provider focuses on the hard reasoning step.

TUI and interaction