What can you do with this server?

SAGE is a token-saving AI coding agent assistant that compresses terminal output, manages command history, and provides agentic error recovery — all accessible via MCP tools. Command Execution & History * sage_call – Run any shell command with purpose metadata (read, search, test, build, deploy, audit) for quality tracking * sage_agentic_run – Run a command with automatic retry/fix/verify loop on failure (configurable autonomy: suggest, ask, or auto) * sage_get_history – Retrieve recent command history, optionally filtered to failed commands only * sage_show_raw – Recover the exact original (uncompressed) output of any previous run by ID Error Analysis & Fixing * sage_explain_error – Get an AI-friendly explanation of a command error * sage_suggest_fix – Get suggested fixes for a failed command * sage_agentic_fix – Get an auto-fix suggestion with strategy and confidence score * sage_agentic_session – Inspect the current agentic session state (failure streak, recent errors, intent chain) File Operations (Token-Efficient) * sage_read_file – Read files with SAGE compression; supports line ranges and symbol-only outlines * sage_write_file – Create or update a file, returning a compact confirmation instead of echoing full content * sage_edit_file – Perform exact string replacement with a compact change preview and automatic pre-edit snapshot for undo Search & Navigation * sage_grep – Search files with compressed, grouped results preserving exact paths and line numbers * sage_glob – Find files by glob pattern (newest first, junk directories ignored, capped output) * sage_tree – Get a compact, depth-limited directory overview Agents & Workflows * sage_spawn_agent – Spawn a specialized sub-agent for a task (types: code, test, debug, security, performance) * sage_run_workflow – Execute a named workflow pipeline (e.g., test, ci, deploy) or a custom workflow YAML file All operations prioritize token efficiency by compressing output and keeping raw logs local, while an agent firewall blocks destructive commands and detects secret exposure.

SAGE

by PsYcGoD

Overview Schema Related Servers Score Discussions

Python

Local

SAGE is a token-saving AI coding agent assistant that compresses terminal output, manages command history, and provides agentic error recovery — all accessible via MCP tools.

Command Execution & History

sage_call – Run any shell command with purpose metadata (read, search, test, build, deploy, audit) for quality tracking
sage_agentic_run – Run a command with automatic retry/fix/verify loop on failure (configurable autonomy: suggest, ask, or auto)
sage_get_history – Retrieve recent command history, optionally filtered to failed commands only
sage_show_raw – Recover the exact original (uncompressed) output of any previous run by ID

Error Analysis & Fixing

sage_explain_error – Get an AI-friendly explanation of a command error
sage_suggest_fix – Get suggested fixes for a failed command
sage_agentic_fix – Get an auto-fix suggestion with strategy and confidence score
sage_agentic_session – Inspect the current agentic session state (failure streak, recent errors, intent chain)

File Operations (Token-Efficient)

sage_read_file – Read files with SAGE compression; supports line ranges and symbol-only outlines
sage_write_file – Create or update a file, returning a compact confirmation instead of echoing full content
sage_edit_file – Perform exact string replacement with a compact change preview and automatic pre-edit snapshot for undo

Search & Navigation

sage_grep – Search files with compressed, grouped results preserving exact paths and line numbers
sage_glob – Find files by glob pattern (newest first, junk directories ignored, capped output)
sage_tree – Get a compact, depth-limited directory overview

Agents & Workflows

sage_spawn_agent – Spawn a specialized sub-agent for a task (types: code, test, debug, security, performance)
sage_run_workflow – Execute a named workflow pipeline (e.g., test, ci, deploy) or a custom workflow YAML file

All operations prioritize token efficiency by compressing output and keeping raw logs local, while an agent firewall blocks destructive commands and detects secret exposure.

SAGE - Smart Agent Guidance Engine

Python PyPI npm License

SAGE is a local-first command wrapper for AI coding agents. It keeps full terminal output on your machine, sends agents a clean compressed summary, and tracks proof metrics without uploading your raw logs.

Use it with Claude Code, Codex, Cursor, Windsurf, OpenCode, Cline, custom agents, CI scripts, and normal terminal workflows.

Start Here: Install SAGE, Use once sage run -- python -m pytest, Then Use Any AI Agent

Package installation is passive for package-registry safety. After installing, run sage install once to connect this machine and activate SAGE for supported local AI agents.

PyPI / pip

pip install psycgod-sage
# or
python -m pip install --upgrade psycgod-sage
sage install
sage run -- python -m pytest

npm / npx

npm install -g psycgod-sage
npx -y psycgod-sage install
npx -y psycgod-sage run -- npm test

After install, restart any open AI-agent sessions. New sessions should read the SAGE instructions automatically and route terminal commands through SAGE.

Example prompt after restarting your AI agent:

Please help me with my general book in this folder.

Natural shortcuts also work:

sage pytest
sage npm test
sage git status

These are treated as:

sage run -- pytest
sage run -- npm test
sage run -- git status

Related MCP server: knitbrain

What SAGE Does

Step	Result
`sage install`	Connects the machine, repairs global/project agent instructions, and verifies activation
`sage run -- <command>`	Runs the command, stores raw output locally, and returns a compact useful summary
Agent memory/hooks	Tell supported AI agents to use SAGE for noisy terminal work
Local database	Keeps command history, compression proof, and retry context on the user's machine
Optional cloud proof	Sends aggregate metrics only when connected proof mode is enabled

SAGE does not auto-enable MCP. MCP is optional and manual for users who want it.

Live Proof

Latest pulled stats as of 2026-08-01:

Metric	Value
SAGE telemetry command events	27,892
Tokens processed	799.5M
Tokens saved	783.7M
Compression rate	98.02%
Estimated savings	$16,261.90
Command success rate	88.3%
PyPI downloads, last 7 days	632
npm downloads, last 7 days	362
GitHub clones, last 14 days	574

Live dashboard: sage.api.marketingstudios.in/dashboard Install page: sage.api.marketingstudios.in/install

SAGE public proof dashboard

Why It Helps

AI coding agents burn context on repeated logs, failed test output, install noise, stack traces, and build spam. SAGE sits between the command and the agent.

Without SAGE	With SAGE
Agent sees full noisy terminal output	Agent sees the useful summary
Context disappears fast	Context lasts longer
Repeated failures waste tokens	Errors are grouped and explained
Raw logs may enter prompts	Raw logs stay local
Hard to prove savings	SAGE records proof metrics

Distribution

Channel	Package	Status
PyPI	`psycgod-sage`	Canonical Python package
npm / npx	`psycgod-sage`	Node launcher for the Python core
MCP Registry	`io.github.PsYcGoD/sage`	Optional/manual MCP entry
Glama	`PsYcGoD/sage`	Optional/manual hosted MCP listing

The npm package delegates to the Python implementation so both install paths use the same local database, telemetry rules, compression, and command behavior.

Common Commands

sage install                       # Activate this machine and AI-agent instructions
sage doctor --activation           # Verify activation
npx -y psycgod-sage doctor --activation
sage run -- <command>              # Wrap any command
sage run --cwd /project -- <command> # Explicit workspace for host integrations
sage pytest                        # Shortcut for: sage run -- pytest
sage npm test                      # Shortcut for: sage run -- npm test
sage git status                    # Shortcut for: sage run -- git status
sage context stats                 # Token savings summary
sage context report                # Full compression report
sage history --limit 10            # Recent command history
sage explain --failed              # Explain the latest failed command
sage suggest --failed              # Suggest the next fix
sage fix --apply                   # Try an automatic fix
sage ml setup                      # Optional ML V2 dependencies
sage mcp install                   # Optional/manual MCP config
sage dashboard start               # Local dashboard

Privacy Modes

Mode	Requires login?	Sends data?	What leaves the machine?
Local-only	No	No	Nothing
Connected proof	Machine auth	Yes	Aggregate counters and proof metrics
Debug telemetry	Optional	Opt-in only	Redacted diagnostic summaries

SAGE is designed to keep prompts, source code, credentials, raw command output, and project files local unless the user deliberately enables a feature that requires sending data.

Known Limitations

Limitation	What To Do
Already-open AI-agent sessions may not reload new instructions	Restart Claude/Codex/Cursor/Windsurf/OpenCode after `sage install`
Locked-down host apps can disable shell tools	SAGE cannot enable tools the host application has blocked
A host starts its shell in the wrong folder	Pass `sage run --cwd <project> -- <command>` or set `SAGE_WORKSPACE_CWD`
npm/PyPI installs cannot safely auto-run activation	Run `sage install` once after package install
MCP can disconnect in some stdio agent sessions	Use normal `sage run -- <command>` by default; enable MCP manually only if needed
Package installs are passive by design	Real activation starts with `sage install`

Demos

Flow	Preview
PyPI install
npm install
`sage run --`
CLI run

License

MIT. See LICENSE.

Install Server

license - permissive license

quality

maintenance

How are these scores calculated?

Maintenance

–Maintainers

–Response time

1dRelease cycle

27Releases (12mo)

Commit activity

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Tools

View all tools

Related MCP Servers

terminal-mcp
ParthKapoor-dev
F
license
-
quality
-
maintenance
A secure and pluggable MCP server to run terminal commands on your local machine or cloud server — remotely, safely, and with LLMs or agentic clients.
Last updated 2025-07-22
knitbrain
Developer Tools Knowledge & Memory
PDgit12
A
license
A
quality
A
maintenance
Local-first MCP server that gives any AI coding agent per-project memory, workflow intelligence, and always-on, lossless token & context optimization.
Last updated 2026-07-08
37
35
3
MIT
veil-mcp
Shell Access Command Line
vkmtx
A
license
A
quality
B
maintenance
An agent-native shell as an MCP server, designed for LLM agents (like Claude Code) to execute commands with structured output, lazy detail retrieval, and effect tracking, minimizing token usage.
Last updated 2026-08-03
9
12
MIT
SuperBased Observer
Monitoring Observability
superbasedapp
F
license
-
quality
A
maintenance
Local MCP server that lets your AI coding agent query its own cross-tool project history - file/command freshness, past test failures, cost & token spend, cache status, and session handoff - over stdio, 100% local, no telemetry.
Last updated 2026-08-01
36

View all related MCP servers

Related MCP Connectors

XMemo
User-owned memory for AI agents, Copilot, Claude, IDEs, CLIs, and chat apps over remote MCP.
Darwin RAG
Local-first RAG engine with MCP server for AI agent integration.
RogerRat
Real-time chat hub for AI agents — Claude Code, Cursor, Cline, Codex over MCP or REST.

View all MCP Connectors

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/PsYcGoD/sage'

If you have feedback or need assistance with the MCP directory API, please join our Discord server