Engram
io.github.NickCirvPublished by GitHub account NickCirvv4.5.0Updated Oct 24, 2026
Ranked local code-graph context for AI coding agents. Intercepts reads + greps. Apache-2.0.
The publisher's own server: Engram
Overview
Engram builds a local structural code graph of a project so an AI coding agent can retrieve focused code context instead of reading whole files.
- What you can do
- Engram indexes source entities, Git relationships and selected project memory into a project-local SQLite graph, then answers queries with matching entities and an estimated token count. Its CLI exposes commands for exploring structure (query, path, gods, callers, callees, impact, stats), maintaining context (init, watch, reindex, learn, mistakes), generating agent documents, and serving context over MCP or a local dashboard. It also offers hook integration that can intercept reads and greps, and a mistake guard that warns or denies.
- When to use it
- Worth adding when an assistant works on a large codebase and you want it to locate relevant code and relationships before opening full files, or to carry recorded mistakes into a later session. Start with the graph and inspect its output before enabling hooks or other integrations.
- Requirements
- Runs as a local Node.js process (package engramx, Node >= 20) over stdio. Indexing writes a .engram/ graph inside the project. Optional environment variables include ENGRAM_ANTHROPIC_MEMORY_PATH, ENGRAM_MCP_CONFIG_PATH, ENGRAM_MISTAKE_GUARD, ENGRAM_NO_UPDATE_CHECK and the secret ENGRAM_API_TOKEN for the local HTTP server. No account or authentication is declared for the MCP server itself.
Installation
In SourceWeft
- Open Engram in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
[Engram — Nicholas Ashkar repository collection]
Engram
A local structural code graph and context toolkit for AI coding agents. Engram indexes source entities, Git relationships and selected project memory, then exposes focused context through a CLI, agent hooks, MCP and an authenticated local dashboard.
Use it to find relevant code before reading full files, inspect relationships and carry recorded mistakes into a later session. Read the source returned by a query before making a behavioral claim: graph retrieval is an aid to investigation.
Quickstart
The inspected package is engramx 4.5.0 and requires Node >=20. This source-build example is source-inspected, not executed; it does not assume a currently published package or extension version.
Replace ../your-project with a codebase you can inspect. Indexing writes the project's .engram/ graph. The --no-hook flag matters: the default CLI init also installs a Sentinel hook. Start with the graph, examine the output, then decide which integration to enable. The build includes grammar bundling; inspect package scripts and dependencies before installation.
The query returns matching graph entities and an estimated token count, or a no-matching-nodes message. Counts depend on the indexed project; no benchmark output is fabricated here.
What is implemented
These entry points are declared in the pinned CLI. Consult each command's help before a write operation. Generators, hook installers, cache/database commands and plugin installation can modify local state.
Architecture
Source miners extract entities, references, Git co-change and selected mistake/session information. The graph store persists project-local SQLite using sql.js. Queries traverse the graph and render bounded context. The provider resolver combines built-in sources and optional plugins/MCP providers; integrations can add external processes and network access.
The architecture and integration guide maps these paths, documents HTTP authentication and gives a local MCP configuration. Existing design records, release notes, integration documents and the ECP draft remain linked in the documentation inventory. They retain historical context and are not all certified against this revision.
Privacy and operational boundaries
The core graph is local, but the entire system is not guaranteed to be network-free. The CLI has npm update checks, Context7 can call an external wrapper, and configured MCP/plugin providers can execute their own processes. ENGRAM_NO_UPDATE_CHECK=1 disables the update-check path; it does not disable every optional integration. Review configured providers and the agent that receives graph output.
The HTTP server binds to 127.0.0.1, validates Host/Origin and requires a bearer token or dashboard cookie for protected routes. It resolves a token from ENGRAM_API_TOKEN or a local token file. Keep that token private and retain the existing security policy.
Limits and measurement
Structural context size, estimated token reductions, session replay and actual provider billing answer different questions. A smaller packet does not by itself demonstrate equal answer quality or a lower bill. Reproduce the included benchmarks on your own representative workload and track correctness alongside cost. This documentation review did not run a build, test suite, benchmark or agent session.
Development
The repository contains unit and integration test sources for graph storage, providers, hooks, HTTP security and other modules. Their presence is evidence of test coverage intent; results at this revision remain unverified here. See the preserved contribution guide before changing behavior.
License and author
Apache-2.0 license. The ECP specification carries its own attribution and licensing in its source document; this rewrite does not alter either.
Nicholas Ashkar · Applied AI, systems and consulting.
User guides
User manual covers setup, skills, troubleshooting and removal. Sentinel explains current hook behavior and guard modes. Tool authors can use the integration guide.
Source: README.md at commit df445d3
Tools
0Version history
1- v4.5.0LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Other Engram integrations
Engram
tools.engramOfficial publisher
Engram gives AI assistants a shared memory layer that persists across tools, sessions, repositories and teammates.
Engram
Published by GitHub account TushaeBXN
Local, private long-term memory for AI: verbatim, searchable, correctable. No LLM or API key.
Engram: AI memory you can edit in Obsidian
Published by GitHub account engram-app
Hosted MCP memory server that gives Claude, ChatGPT and other MCP clients shared notes they can read and write, editable in Obsidian or the web app.
Engram
Published by GitHub account devinmlowe
Engram is a local-first cognitive memory server for coding agents: it captures conversations, extracts structured knowledge, and serves hybrid recall, graph and
Engram
Published by GitHub account tstockham96
Engram gives an AI assistant a local SQLite memory vault with semantic recall, a knowledge graph, and LLM-powered consolidation.