Skip to main content
Glama
nworks3d

thor-memory-bible

by nworks3d
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

Related Servers

Alternatives to thor-memory-bible

  • cogmem

    dcondrey
    A
    license
    A
    quality
    F
    maintenance
    Self-improving, verifiable memory for AI coding agents. Learns how you work, stops repeating mistakes, models each project, recalls the right lesson at the right moment. Every memory is signed and tamper-evident. Local-first.
    8
    2
    Apache 2.0

  • GoodMemory

    hjqcan
    A
    license
    B
    quality
    A
    maintenance
    Local-first, auditable memory for Codex, Claude Code, and MCP clients. It stores scoped user/project memory in SQLite or Postgres, serves read-only recall and inspection tools by default, and supports opt-in governed writeback with review and forget controls.
    8
    635 npm
    18
    MIT

  • memini

    lumayapartners
    A
    license
    A
    quality
    C
    maintenance
    Local-first project memory for AI coding agents. Records failed attempts, fragile files, and decisions per repo, and warns the agent via hooks before it repeats a recorded mistake.
    6
    59 npm
    MIT

  • Sentinela MCP

    luclinocruz
    A
    license
    Not graded
    quality
    C
    maintenance
    Provides coding agents with durable, cross-session lessons-learned memory, enforcing that success or failure verdicts can only come from human approval, human correction, or objective metrics—never from the agent itself.
    Apache 2.0
  • @team-monet/monet by team-monet

    @team-monet/monetofficial

    team-monet
    A
    license
    Not graded
    quality
    A
    maintenance
    Provides a local-first memory layer for coding agents, storing principles, rules, and corrections on-device and surfacing them at the moments they apply so agents act on the intended outcomes without sending data to the cloud.
    15,531 npm
    1
    AGPL 3.0

  • AgentRecall

    AkbarDizaji
    A
    license
    Not graded
    quality
    A
    maintenance
    A local-first memory for AI coding agents. AgentRecall turns the feedback and failures you run into while coding into reusable rules, then serves the right ones back — on the command line or directly to Claude Code over MCP. Everything stays on your machine: no cloud sync, no web UI, no API keys.
    9
    MIT

Related Servers

  • Agent Guardian

    niallsemple
    A
    license
    Not graded
    quality
    A
    maintenance
    Enables AI coding agents to consult persistent local project memory before acting, checking proposals against rejected ideas, repeated failure loops, goal drift, stale assumptions, and evidence-based completion criteria, and returning ALLOW, WARN, or BLOCK decisions so context loss after compaction doesn't cause repeated mistakes.
    MIT

  • rsi-boot

    Apollo-lwx
    A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI coding assistants to persist and recall project-specific conventions, prohibitions, and repair lessons locally, with approved rule injection before tasks and no external API calls.
    MIT

  • CodeNeuro

    kterna
    A
    license
    Not graded
    quality
    B
    maintenance
    Enables autonomous coding agents to just-in-time retrieve scoped architecture contracts and task-specific P0/P1 rules before reading or writing files, record troubleshooting findings from test failures, revoke or downgrade stale short-term rules, propose long-term contract changes for human approval, and list active rules per project and task. Supports multi-project and multi-worktree workflows over MCP with SQLite-backed storage.
    MIT

  • Ibid

    jonasbu11
    A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI assistants to keep a self-managing rulebook and memory in plain Postgres, turning statements their owner makes in passing into binding rules once stated explicitly, about one client, or twice in distinct contexts within 90 days. Rules are recalled widest-first across a tree of spaces and task kinds with the narrower rule winning, while an append-only fact store tracks confidence, salience, and near-duplicate restatements, and everything added on its own is listed with an undo.
    MIT
Deploy Server
Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

TDQS

A4.4/5.0

Scored across 16 tools

Disambiguation5/5

Each tool occupies a clearly distinct niche, and descriptions explicitly cross-reference each other to prevent misselection (get vs lookup vs history, outline vs where_used vs search_code, mark vs revise vs retract). The read/write/judge/lane boundaries are unambiguous.

Naming Consistency4/5

All names are lowercase and consistently styled, but the set mixes bare verbs (mark, pin, revise, remember, retract) with nouns (status, history, library) and only a couple of multi-word names (search_code, where_used). Readable and predictable enough, with minor convention drift.

Tool Count4/5

At 16 tools it sits at the upper edge, but the domain spans memory CRUD, bindings, conflict resolution, a separate library lane, and a code index, so each tool earns its place. No obviously redundant tools.

Completeness4/5

Full item lifecycle is covered (remember/revise/retract/get/lookup/history), plus binding management (pin/unpin), conflict resolution (resolve), judgement (mark), the library lane (shelve/library), and code search. Only minor gaps, such as no explicit bulk listing of bindings or pinned items, which agents can work around via status/lookup.

Maintenance

ActivityActive
ResponsivenessNo issues

Resources