Aegis
About
A deterministic context compiler for AI coding agents. Aegis replaces RAG with a Directed Acyclic Graph (DAG) to strictly enforce software architecture and reduce token consumption by up to 12x.
Details
- Author
- fuwasegu
- Downloads
- 430
- Categories
- Other
Jump to
- Deterministic Context Routing (same input, same context, reproducible).
- Transitive Dependency Resolution (automatically fetches dependent guidelines).
- Dual Surface Architecture (Agent read-only context vs. Admin human review).
- Human-in-the-Loop Knowledge Evolution (proposes DAG updates, approved by humans).
- Massive Token Efficiency (12x reduction in token consumption, 3.5x faster responses in benchmarks).
- Optional Local SLM Expansion (node-llama-cpp engine for semantic intent extraction).
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
AegisCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
After installing and configuring the server, agents invoke Aegis before editing a file; it deterministically traverses the dependency graph and compiles the required context. The exact setup and invocation commands are not detailed beyond the paradigm described.
aegis_compile_context
Compile deterministic context for target files. Returns base documents, resolution path, and templates. v2: delivery-aware with budget control.
aegis_observe
Record an observation event. Writes to Observation Layer only (never Canonical).
aegis_get_compile_audit
Retrieve details of a past compile_context invocation.
aegis_get_known_tags
List distinct intent tags from tag_mappings (approved-resolvable only) with knowledge_version and a SHA-256 tag_catalog_hash of the tag list for client-side caching.
aegis_workspace_status
Read-only workspace snapshot: recent compile regions (from compile_log), unresolved compile_miss observations without proposals, and pending proposal count. Does not mutate Canonical Knowledge.
aegis_init_detect
Analyze a project and generate an initialization preview. Does not modify Canonical.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"aegis": {
"aegis": {
"command": "npx",
"args": [
"-y",
"@fuwasegu/aegis",
"--surface",
"agent"
]
},
"aegis-admin": {
"command": "npx",
"args": [
"-y",
"@fuwasegu/aegis",
"--surface",
"admin"
]
}
}
}
}McpServers
{
"aegis": {
"command": "npx",
"args": [
"-y",
"@fuwasegu/aegis",
"--surface",
"agent"
]
},
"aegis-admin": {
"command": "npx",
"args": [
"-y",
"@fuwasegu/aegis",
"--surface",
"admin"
]
}
}Aegis: The Deterministic Context Compiler for AI Agents
As codebases grow, AI coding agents (like Cursor, Claude Code, and Codex) struggle to find the right architectural guidelines. Traditional RAG (Retrieval-Augmented Generation) suffers from a "semantic gap"—searching for feature keywords often fails to retrieve abstract architectural rules or domain models. This leads to poor code quality, hallucinated architectures, and massive token waste as agents endlessly grep through repositories. Aegis solves this by shifting the paradigm from "probabilistic search" to "deterministic compilation." Instead of relying on vector embeddings, Aegis uses a Directed Acyclic Graph (DAG) backed by SQLite to map file paths and layers directly to your Markdown documentation. When an agent plans to edit a specific file, Aegis deterministically traverses the dependency graph and compiles the exact architectural context required for that specific task.# 🛡️ Key Features
- Deterministic Context Routing: Say goodbye to AI hallucinations. Aegis maps file paths (e.g., app/UseCases/) to specific guidelines. Same input, same context. 100% reproducible. - Transitive Dependency Resolution: If usecase_guidelines.md depends on entity_guidelines.md, Aegis automatically resolves the edges and fetches both. It feeds the AI exactly what it needs, nothing more. - Dual Surface Architecture (Agent vs. Admin): Strict separation of concerns. The agent surface provides read-only context and allows agents to report missing rules. The admin surface is reserved for humans to review and approve knowledge base updates. - Human-in-the-Loop Knowledge Evolution: Agents can self-review and trigger aegis_observe if they lack context. Aegis proposes DAG updates based on these observations, but canonical knowledge is only updated upon human approval. - Massive Token Efficiency: By directly injecting the correct context, Aegis eliminates the hidden costs of agent exploration. In real-world benchmarks, it reduced token consumption by 12x and improved response times by 3.5x. - Optional Local SLM Expansion: Opt-in to the built-in node-llama-cpp engine (Qwen) to extract intent tags from the agent's plan, providing semantic context expansion without compromising the deterministic core. Stop searching. Start compiling**. Aegis acts as your automated Tech Lead, aggressively shielding your codebase's integrity by forcing AI agents to read the rules before they write the code.Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
