codex
by GhostPawJS
README.md
<a href="https://codex.ghostpaw.dev/"><img src="https://raw.githubusercontent.com/GhostPawJS/codex/main/.github/social-preview.png" alt="GhostPaw codex: When one agent saves a wrong fact, every agent trusts it." width="100%"></a>
# @ghostpaw/codex
[](https://www.npmjs.com/package/@ghostpaw/codex) [](https://github.com/GhostPawJS/codex/actions/workflows/ci.yml) [](https://codex.ghostpaw.dev/) [](package.json) [](https://registry.modelcontextprotocol.io/v0.1/servers/io.github.GhostPawJS%2Fcodex/versions/latest) [](https://nodejs.org) [](LICENSE) [](https://aiagentslisting.com/mcp/ghostpaw-codex)
**Agent memory as beliefs with a source, a certainty and a revision history.**
```bash
ghostpaw-codex --help
```
Local, evidence-backed memory for agents. One SQLite file, zero runtime
dependencies.
Codex stores what an agent believes as claims with a source, a certainty,
evidence counts, decay and an honest revision history. Agents search before
they remember, confirm or correct instead of appending, and see which beliefs
are stale, fading or weakly evidenced. It runs as a TypeScript library, an MCP
server, a CLI and an Agent Skill, all generated from the same seven tools.
Website: [codex.ghostpaw.dev](https://codex.ghostpaw.dev/)
The release binary includes its runtime. npm and library use require **Node.js 24+**.
## Install
### Release binary (default)
Each line downloads the latest release asset, checks it against the release's SHA256SUMS and installs `ghostpaw-codex` into `~/.local/bin`. On Linux and macOS the trailing `export` puts that folder on PATH for the current shell only: neither the line nor `install.sh` edits `~/.profile` or any other shell startup file. The Windows script adds its folder to the user PATH (open a new terminal afterwards).
linux-x64:
```sh
curl -fsSL https://raw.githubusercontent.com/GhostPawJS/codex/main/install.sh | sh -s -- --target linux-x64 && export PATH="$HOME/.local/bin:$PATH"
```
linux-arm64:
```sh
curl -fsSL https://raw.githubusercontent.com/GhostPawJS/codex/main/install.sh | sh -s -- --target linux-arm64 && export PATH="$HOME/.local/bin:$PATH"
```
darwin-arm64:
```sh
curl -fsSL https://raw.githubusercontent.com/GhostPawJS/codex/main/install.sh | sh -s -- --target darwin-arm64 && export PATH="$HOME/.local/bin:$PATH"
```
darwin-x64:
```sh
curl -fsSL https://raw.githubusercontent.com/GhostPawJS/codex/main/install.sh | sh -s -- --target darwin-x64 && export PATH="$HOME/.local/bin:$PATH"
```
windows-x64 (PowerShell):
```powershell
irm https://raw.githubusercontent.com/GhostPawJS/codex/main/install.ps1 | iex
```
To keep `~/.local/bin` on PATH in new shells, append it to `~/.profile` once (this is the only step that edits a startup file):
```sh
echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.profile
```
To pin a release instead of taking the latest, pass `--version`:
```sh
curl -fsSL https://raw.githubusercontent.com/GhostPawJS/codex/main/install.sh | sh -s -- --target linux-x64 --version 0.6.0 && export PATH="$HOME/.local/bin:$PATH"
```
```text
$ ghostpaw-codex --version
ghostpaw-codex 0.6.0 (binary, linux-x64)
$ ghostpaw-codex --version --short
0.6.0
$ ghostpaw-codex --version --json
{"name":"ghostpaw-codex","version":"0.6.0","variant":"binary","target":"linux-x64"}
```
`variant` is `binary`, `npm` or `library`; `target` is `null` outside the release binary.
A session with the 0.5.2 linux-x64 binary against a small database of five beliefs:

The same session as an [animated GIF](https://raw.githubusercontent.com/GhostPawJS/codex/main/docs/assets/cli.gif).
Other release installers:
```sh
mise use -g github:GhostPawJS/codex
ubi --project GhostPawJS/codex --exe ghostpaw-codex --in ~/.local/bin
eget GhostPawJS/codex
```
For [aqua](https://aquaproj.github.io/docs/reference/registry-config/), define a
`github_release` package in `aqua.yaml`:
```yaml
registries:
- name: codex
type: local
path: codex-registry.yaml
packages:
- name: GhostPawJS/codex@v0.6.0
registry: codex
```
`codex-registry.yaml`:
```yaml
packages:
- type: github_release
repo_owner: GhostPawJS
repo_name: codex
asset: ghostpaw-codex-{{trimV .Version}}-{{.OS}}-{{.Arch}}.tar.gz
format: tar.gz
replacements: { amd64: x64 }
overrides:
- goos: windows
asset: ghostpaw-codex-{{trimV .Version}}-windows-{{.Arch}}.zip
format: zip
files:
- name: ghostpaw-codex
```
Install scripts verify SHA256SUMS. To verify a downloaded archive's
[build attestation](https://cli.github.com/manual/gh_attestation_verify):
```sh
gh attestation verify <archive> -R GhostPawJS/codex
```
Set `GHOSTPAW_VERIFY=attestation` for attestation verification in `install.sh`.
Binaries are unsigned; macOS binaries carry an ad-hoc signature. For a browser
download on macOS, remove quarantine with
`xattr -d com.apple.quarantine /path/to/ghostpaw-codex`.
Linux binaries require glibc 2.28+; use npx on Alpine.
See the [binary build workflow](.github/workflows/release-binaries.yml).
Approximate sizes for 0.5.2 (Node 26.12.1 inside each binary):
| Target | Archive | Binary |
|---|---|---|
| linux-x64 | 41.7 MB tar.gz | 117.4 MB |
| linux-arm64 | 41.2 MB tar.gz | 115.2 MB |
| darwin-arm64 | 44.8 MB tar.gz | 146.7 MB |
| darwin-x64 | 46.4 MB tar.gz | 149.5 MB |
| windows-x64 | 38.4 MB zip | 105.6 MB |
The npm package is about 920 KB unpacked and needs Node 24+. Every release is
installed and run on ubuntu-24.04, macos-15 and windows-2025 by the
[install check](.github/workflows/install-check.yml).
### npx / npm (for npm-based environments)
The [npm package](https://www.npmjs.com/package/@ghostpaw/codex) requires Node 24+:
```sh
npm install -g @ghostpaw/codex
npx -y @ghostpaw/codex --help
```
### Library (for harnesses embedding it in code)
Requires Node 24+:
```sh
npm install @ghostpaw/codex
```
```ts
import { initCodexTables, read, write } from '@ghostpaw/codex';
```
See [Library usage](#library).
## Running inside sandboxed agent harnesses
Inside a Codex CLI `--sandbox workspace-write` session, the database and its
parent directory must be inside a writable root, including SQLite's `-wal` and
`-shm` side files. A default DB under `~/.ghostpaw` outside those roots can fail
with `SQLITE_CANTOPEN` or `EPERM` (often exit 70; directory creation failures
may exit 2), even when normal shell permissions allow access. Put the DB inside the workspace with `--db ./state/codex.db`,
or set `GHOSTPAW_CODEX_DB="$PWD/state/codex.db"` for CLI/MCP use.
To use an external DB directory, add it when starting the OpenAI Codex CLI
(replace `<dir-with-db>` with its absolute path):
```sh
codex exec --sandbox workspace-write --add-dir <dir-with-db> "Run the GhostPaw CLI"
```
Alternatively, set `sandbox_workspace_write.writable_roots` in
`~/.codex/config.toml` before starting the session:
```toml
[sandbox_workspace_write]
writable_roots = ["/absolute/dir-with-db"]
```
## 30-second quickstart
### MCP server
Every client below starts the same stdio server: `ghostpaw-codex mcp`.
Use the full executable path if its folder is not on PATH.
For npm-based environments, use `npx -y @ghostpaw/codex mcp`.
Beliefs live in `~/.ghostpaw/codex.db` unless the `GHOSTPAW_CODEX_DB`
environment variable (absolute path) or `--db <path>` says otherwise.
**Claude Code**
```bash
claude mcp add ghostpaw-codex -- ghostpaw-codex mcp
```
or as a plugin, which also installs the skill:
```bash
/plugin marketplace add GhostPawJS/codex
/plugin install ghostpaw-codex@ghostpaw-codex
```
**Codex CLI** (`~/.codex/config.toml`)
```toml
[mcp_servers.ghostpaw-codex]
command = "ghostpaw-codex"
args = ["mcp"]
```
**Cursor** (`.cursor/mcp.json`), **Claude Desktop** (`claude_desktop_config.json`)
or a project `.mcp.json`:
```json
{
"mcpServers": {
"ghostpaw-codex": {
"command": "ghostpaw-codex",
"args": ["mcp"]
}
}
}
```
**Cline** (MCP Servers → Configure MCP Servers, `cline_mcp_settings.json`).
VS Code often starts without `~/.local/bin` on PATH, so use the absolute path
that `echo "$HOME/.local/bin/ghostpaw-codex"` prints (PowerShell:
`"$env:LOCALAPPDATA\Programs\ghostpaw\bin\ghostpaw-codex.exe"`). Merge the
entry into the existing `mcpServers`. Settings file locations, the
`cline mcp add` form and checks: [llms-install.md](llms-install.md).
For Cline CLI 3.x, `cline config mcp` lists the configured servers.
```json
{
"mcpServers": {
"ghostpaw-codex": {
"command": "/absolute/path/to/ghostpaw-codex",
"args": ["mcp"],
"env": { "GHOSTPAW_CODEX_DB": "/absolute/path/to/.ghostpaw/codex.db" }
}
}
}
```
Claude Desktop users can also install `server.mcpb` from the
[latest GitHub release](https://github.com/GhostPawJS/codex/releases/latest).
A Dockerfile is included for container hosts:
`docker build -t ghostpaw-codex . && docker run -i --rm -v codex:/data ghostpaw-codex`.
The server speaks MCP 2026-07-28 (stateless, `server/discover`) and the
initialize-based revisions 2025-11-25, 2025-06-18, 2025-03-26 and 2024-11-05.
## CLI
```text
ghostpaw-codex search <query> [--limit N --min-score N --category C --source S]
ghostpaw-codex review <flags|status|log|trends> [--limit N --now N]
ghostpaw-codex belief add <claim> --source S --category C [--certainty N --provenance P]
ghostpaw-codex belief show <beliefId>
ghostpaw-codex belief retire <beliefId>
ghostpaw-codex belief confirm|correct|forget|defer <beliefId> [flags]
ghostpaw-codex belief merge <beliefIds...> [flags]
ghostpaw-codex proximity dismiss <beliefA> <beliefB>
ghostpaw-codex mcp|skill|tools|describe|call|completions|version|help
```
Belief additions include a nearest-belief hint when an active belief has similarity of at least 0.7; use it to confirm or merge related claims.
WARNING: `belief retire` hard-deletes the whole lineage (the belief and all its predecessors/successors) and cannot be undone. Use `belief forget` for soft removal that keeps lineage. Every retire invocation warns on stderr.
`--json` is accepted on every read command, including all review views, belief show, alias list, tools, describe, version, help and skill guides. Set `GHOSTPAW_OUTPUT=json` to opt all commands into JSON output as if `--json` were passed. Other values or an unset variable preserve default output, including when stdout is piped or a TTY.
Global flags can appear anywhere: `--db <path>`, `--json`, `--quiet`,
`--compact`, `--help`/`-h`, `--version`/`-V`/`-v`, `--no-color`.
`NO_COLOR` is accepted; output uses no terminal colors.
Noun-verb commands print short text by default, including when stdout is piped.
Search and review lists show one belief per line: `id claim [certainty source strength]`.
Flags append reason codes; the log shows `id type claim`. Add, show, correct and
merge show aligned detail fields and nearby beliefs. Status and trends show
aligned `key: value` lines. `--json` prints the full tool result and `--compact`
removes JSON indentation. Legacy tool invocation keeps its JSON output.
`--quiet` prints only result ids for search, review flags and log, and the affected
belief id for writes; status, trends and version print nothing.
Use `help belief`, `belief --help` or `belief correct --help` for schema-derived
help. Each revision verb accepts only the flags it uses. Correction takes
`--claim`; forgetting also accepts `--successor-id`. Deferral accepts
`--deferred-until` as YYYY-MM-DD, DD.MM.YYYY, today, tomorrow, +3d, an ISO
date-time with timezone, or epoch milliseconds. Calendar dates resolve to local
end of day and must be in the future.
Array flags repeat, kebab-case flags map to schema properties, and values are literal, including leading `@`. Use JSON stdin (`-`) for long input. `--` ends flags. Except for raw belief import, a positional `-`, or piped stdin
with no arguments, reads a JSON object; explicit flags override its fields.
Database selection uses `--db`, `GHOSTPAW_CODEX_DB`, then `~/.ghostpaw/codex.db`.
Opening the default database prints `using default db <path>` once on stderr.
Suppress the notice with `--quiet` or `GHOSTPAW_QUIET=1`. Commands that do not open a database print no notice.
Top-level help shows the resolved path. Version output starts with
`ghostpaw-codex` and identifies binary target, npm or library execution.
`ghostpaw-codex skill` prints the full skill reference. Use
`ghostpaw-codex skill --list` to list workflow guides and
`ghostpaw-codex skill capture-beliefs-well` to read a guide. `skill --help`
shows these forms; unknown guide names include a suggestion.
| Exit | Noun-verb result |
|---|---|
| 0 | Success, including no_op |
| 1 | Tool error |
| 2 | Usage or schema error |
| 3 | Clarification needed or not found |
| 4 | Conflict or version mismatch |
| 70 | Internal error |
Errors and recovery hints go to stderr. Clarification prints the question and missing flags to stderr. With `--json`, usage and internal errors also print
`{ok:false,error:{code,message}}` to stdout. Tool results retain their full
shape. Legacy `tools [--json]`, `describe <tool>`, `call <tool> [JSON|-]`
and `<tool_name> --parameter value` keep their existing exit codes.
`completions bash`, `completions zsh` and `completions fish` print shell scripts.
```sh
ghostpaw-codex belief add "Deploys go out on Tuesdays" --source explicit --category procedure
```
```sh
ghostpaw-codex search "when do we deploy" --json | jq '.data.results'
```
```sh
printf '%s' '{"beliefId":1}' | ghostpaw-codex belief show - --json
```
### File values and leading @
File input is opt-in for each CLI argument. When an argument's help lists
`(@file, @- stdin, @@ literal @)`, `@path` reads a UTF-8 file, `@-` reads
stdin, and `@@text` passes the literal value `@text`.
The belief import input enables this option. Other Codex arguments do not: flags and positional values
keep leading `@` and `@@` as written. For long claims, pass a JSON object
through stdin with `-` (see the example above).
### Agent Skill
`SKILL.md` (repo root) and `skills/codex/SKILL.md` follow the
[Agent Skills](https://agentskills.io) format and ship in the npm package.
Copy `skills/codex/` into your agent's skills folder, or print it:
```bash
ghostpaw-codex skill > SKILL.md
```
### Library
```bash
npm install @ghostpaw/codex
```
```ts
import { DatabaseSync } from 'node:sqlite';
import { initCodexTables, read, write } from '@ghostpaw/codex';
const db = new DatabaseSync('codex.db');
initCodexTables(db);
const { id } = write.remember(db, {
claim: 'The API uses GraphQL with a REST fallback.',
source: 'explicit',
category: 'fact',
});
write.confirmBelief(db, id);
write.correctBelief(db, id, {
claim: 'The API uses GraphQL exclusively; REST was retired.',
source: 'observed',
category: 'fact',
});
read.recall(db, 'graphql api'); // ranked, lineage-aware
read.listFlags(db); // stale, fading, low-trust, single-evidence
```
Wire the same tools into any LLM SDK. Each tool carries a JSON Schema:
```ts
import { tools } from '@ghostpaw/codex';
for (const tool of tools.codexTools) {
// tool.name, tool.description, tool.inputSchema, tool.handler(db, input)
}
```
Or embed the MCP server in your own process:
```ts
import { createCodexMcpServer } from '@ghostpaw/codex/mcp';
const server = createCodexMcpServer({ dbPath: './codex.db' });
```
## Docs
The live demo runs the library in your browser against an in-memory SQLite database. Each view below opens a different part of it:
- [Dashboard](https://codex.ghostpaw.dev/docs/): integrity score and recent beliefs
- [Capture](https://codex.ghostpaw.dev/docs/#/capture): record a belief and see close matches you already hold
- [Flags](https://codex.ghostpaw.dev/docs/#/flags): beliefs flagged for review: confirm, correct or forget
- [Activity Log](https://codex.ghostpaw.dev/docs/#/log): activity log of every write
## Why not MEMORY.md?
A markdown memory file works until it doesn't:
- **It only grows.** Agents append, rarely delete, and the file ends up in
every prompt. Codex returns the few beliefs that match a query
(FTS5 bm25 plus hashed character-trigram similarity, IDF-weighted with a 55% relative cutoff).
- **Contradictions pile up.** "We use REST" and "REST was retired" sit side by
side. Codex detects near-duplicates on every write, and corrections
supersede the old belief while keeping the lineage.
- **Everything looks equally true.** A guess and a confirmed fact read the
same in prose. Codex tracks source (explicit, observed, distilled,
inferred), certainty and evidence count, and flags what is stale or weakly
supported.
- **No time.** Codex decays freshness, so old beliefs surface for review
instead of quietly steering behaviour.
- **Concurrent edits.** Two agents writing one file clobber each other. Codex
is a SQLite database in WAL mode.
It stays local: one file you can copy, back up or inspect with any SQLite tool.
No server, no API key, no network.
## Tools
| Tool | What it does |
|---|---|
| `search_codex` | Lexical recall with FTS5 bm25 and character-trigram similarity |
| `review_codex` | Dashboards: flags, status, trends, log |
| `inspect_codex_item` | One belief in full: metrics, lineage, nearby beliefs |
| `remember_belief` | Capture a claim with source, category and provenance |
| `revise_belief` | Confirm, correct, forget, defer or merge |
| `retire_belief` | Hard-delete for privacy or cleanup |
| `dismiss_proximity` | Mark two nearby beliefs as intentionally distinct |
Results are structured (`outcome: success | no_op | needs_clarification |
error`) with entities, next-step hints and recovery advice. The MCP server,
CLI, SKILL.md and plugin manifests are generated from this registry
(`npm run surfaces`) and drift-checked in CI.
## Performance
Measured with `npm run bench` on Node 24.14.0, Linux, Intel Xeon (shared
cloud vCPU), 10,000 beliefs in a file-backed database:
| Operation | p50 | p95 |
|---|---:|---:|
| `search_codex` (tool) | 3.6 ms | 5.0 ms |
| MCP `tools/call` search, stdio framing included | 3.8 ms | 4.2 ms |
| `read.recall` | 3.7 ms | 4.8 ms |
| `inspect_codex_item` | 3.5 ms | 3.8 ms |
| `write.remember` (includes proximity scan) | 4.5 ms | 5.6 ms |
| `review_codex` | 11.7 ms | 13.2 ms |
Cold start (process spawn to first response, median): `--version` 26 ms,
MCP `server/discover` 24 ms, first search against the 10,000-belief file
53 ms. Seeding 10,000 beliefs takes 2.2 s on disk.
Gzip sizes and cold-start medians are budgeted in `budgets.json` and enforced
by `npm run check`.
## The model
| Concept | Purpose |
|---|---|
| **Belief** | A claim held with certainty, evidence, provenance, decay and revision lineage |
| **Dismissal** | A record that two beliefs close by character-trigram vectors are intentionally distinct |
| **Flag** | A derived attention signal: stale, fading, low-trust, single-evidence or gap |
| **Proximity** | Lexical nearness between beliefs (character-trigram vectors), detected on write |
| **Lineage** | The revision chain from corrections and supersessions, with version diffs |
State is derived, never toggled: freshness, strength, review priority and flags
are computed at read time.
## Package surface
| Import | Contents |
|---|---|
| `@ghostpaw/codex` | `initCodexTables`, `read`, `write`, `tools`, `skills`, `soul`, all types |
| `@ghostpaw/codex/mcp` | `createCodexMcpServer`, `serveCodexMcp`, generic MCP server helpers |
| `ghostpaw-codex` (bin) | Noun-verb CLI, legacy tool forms, `mcp`, `skill`, shell completions |
| `dist/mcp-server.js` | Standalone stdio MCP server entry (used by the MCP Bundle and the Dockerfile) |
| `SKILL.md`, `skills/codex/` | Agent Skill with 17 workflow references |
ESM and CommonJS, with type declarations for both.
## Documentation
| Document | Audience |
|---|---|
| [HUMAN.md](docs/HUMAN.md) | Developers using the `read` / `write` API |
| [LLM.md](docs/LLM.md) | Agent builders wiring `soul`, `tools` and `skills` |
| [docs/README.md](docs/README.md) | Architecture: model, invariants, scoring, source layout |
| [docs/entities/](docs/entities/) | Per-entity manuals with exact public API listings |
| [CHANGELOG.md](CHANGELOG.md) | Release history |
## Development
```bash
npm install
npm run check # types, lint, zero-deps, tests, build, surfaces, size, API, consumer, startup, ratchet
npm run bench # hot-path benchmarks at 10,000 beliefs
npm run surfaces # regenerate SKILL.md, plugin manifests, server.json, mcpb manifest
```
`npm run check` is the single gate, locally and in CI. Size budgets
(`budgets.json`) and the public API snapshot (`api-surface.json`) can only
grow with an explicit approval tag in the commit message. The repo is pinned
to Node 24.14.0 via `.nvmrc`.
### Support
If this package helps your project, consider sponsoring its maintenance:
[](https://github.com/sponsors/Anonyfox)
---
**[Anonyfox](https://anonyfox.com) • [MIT License](LICENSE)**
## Query aliases
Search is lexical: FTS5 bm25 plus hashed character-trigram similarity, with
IDF-like token weighting and a 55% relative cutoff. It does not provide semantic
understanding. In corpora of at least 20 active beliefs, queries matching only common terms return at most three results
with a `partial_match` warning.
Aliases are off by default (the table starts empty). Add directed, one-hop aliases
when query vocabulary differs from stored claims:
```sh
ghostpaw-codex alias add class warrior
ghostpaw-codex alias list
ghostpaw-codex alias remove class warrior
```
The library equivalents are `write.addQueryAlias(db, term, alias, options?)`,
`write.removeQueryAlias(db, term, alias)` (returns whether removed), and
`read.listQueryAliases(db)` (sorted `{ term, alias, createdAt }` records).
Both words are normalized with `normalizeClaim` and must be distinct single words.
Adding an existing pair preserves its creation time; `options.now` sets the time
on first insertion. Expansion is deduplicated and never follows alias chains;
the query vector uses the original query.
### Provenance and revision compatibility
Belief records include `provenanceSources`, an append-only list of distinct origin
references. Every write with `--provenance` adds a reference, including duplicate
adds and unchanged corrections. Corrections and merges carry all sources forward.
The legacy `provenance` field remains readable with its existing single-value
behavior; use `provenanceSources` for the complete history.
Superseded-belief errors and `belief show` identify the current active successor.
Library details also expose `activeSuccessorId`, while `supersededBy` retains the
immediate lineage link. Correcting to the same normalized claim and metadata
returns `no_op`. A merge into `--successor-id` can omit `--claim`.
`belief --help` lists belief verbs. `review flags --now +8d` and
`review flags --now 2026-11-10` accept the same date formats as deferral, including
historical dates and epoch milliseconds. Relative day offsets also accept `-3d`
and `30d`. Calendar dates and relative days use local end of day.
New CLI and MCP database files use mode `0600`; newly created parent directories
use `0700`. Existing permissions are preserved. On first upgrade, legacy active
normalized duplicates consolidate into the oldest id, preserving summed evidence,
source references and lineage. Later `--allow-duplicate` additions remain separate.
Merge fan-in alone does not trigger `unstable`; repeated corrections still do.
Search treats punctuation literally; wrap the whole query in double quotes for a phrase.
Use `search --fts 'alpha OR beta'` for raw FTS5 syntax, or
`search note --prefix "project:"` to filter claims by a case-insensitive prefix
after leading whitespace. A query is required with `--prefix`. Library recall
options and search tool inputs also accept `fts` and `prefix`.
Default search ranks claims whose entity before the first colon matches the leading
query tokens first, ignoring case and treating spaces and hyphens alike (for example,
`Agentpreneur: ...` for `Agentpreneur state files routine memory db`). This also
applies with `--prefix`; `--fts` and quoted phrase ranking remain unchanged.
Review status integrity remains the percentage of active beliefs with certainty
at least 0.7. The new, unconfirmed count covers beliefs with one evidence item
younger than seven days; it overlaps the existing strength counts.
Review: `review status --by-prefix` counts active claim prefixes; `review duplicates --limit 20` lists nearby active pairs immediately, honoring dismissals.
`review duplicates` suggests only pairs with the same normalized colon prefix or leading entity by default (case-insensitive, including multiword and hyphenated prefixes). Unprefixed claims pair with other unprefixed claims. Use `review duplicates --cross-entity` (`crossEntity: true` in `review_codex`) to include pairs across entities as before. Suggestions do not change beliefs; inspect each pair before merging or forgetting.
Belief JSON keeps the existing `strength` display tier and adds `integrityTier`, the certainty-only tier used by `review status`. Display `strength` is `strong` when certainty >= 0.4 and freshness >= 0.7; otherwise it falls back to the certainty tier. Thus certainty >= 0.7 always displays `strong`, even when stale. `integrityTier` is `strong` at certainty >= 0.7, `fading` at >= 0.4, otherwise `faint`. Integrity counts strong active beliefs divided by all active beliefs. Human `belief show` labels these as `display strength` and `integrity tier`; a fresh inferred belief at certainty 0.5 can display strong while its integrity tier is fading.
### Batch import and topics
`ghostpaw-codex belief import @beliefs.jsonl --json` reads a UTF-8 JSON Lines
file or JSON array. Use `belief import - --json` (or `@-`) for raw stdin. Each item has
`claim`, `source`, `category` and optional `certainty`, `provenance`, `topic`,
`allowDuplicate`, matching belief add. `--dry-run` runs the same writes and
rolls back, returning provisional IDs. An empty batch succeeds without writes.
The `import_beliefs` tool accepts `{items: [...]}` or `{input: "JSON/JSONL text"}`,
plus optional `dryRun`. Library: `write.importBeliefs(db, items, {dryRun})`.
The whole batch is atomic. Success returns `data.items` with zero-based `index`,
`id`, and `duplicate` when reused. Any item error rolls back the entire batch;
the tool returns `error.details.items` with each item's error, including rollback
status for otherwise valid items. Rolled-back IDs are omitted. Malformed JSON
is rejected before any write; malformed JSON Lines errors identify the line.
Imports preserve the normal normalized duplicate policy and provenance history.
`belief add --topic work` and `belief correct <id> --claim TEXT --topic work`
set an exact topic label. Corrections inherit omitted topics; merges inherit
the primary belief's topic (or existing successor's) unless supplied. Duplicate
adds keep the existing ID and update topic when explicitly supplied. Topics
must be non-empty strings. Existing databases gain a nullable topic column
idempotently; unset topics are omitted from JSON, preserving existing output.
Use `search QUERY --topic work`, `review list --topic work`, or
`read.listBeliefs(db, {topic: "work"})`. Tool inputs accept the same topic field;
`review_codex` view `list` lists active beliefs by ID, default limit 20.
### Unstable revision history
The `unstable` flag is derived at read time when a correction-connected lineage
contains more than two beliefs (normally the original plus two corrections).
Legacy supersessions without a reason also count; merge-only edges do not.
It signals revision history worth inspecting, not a false claim or low certainty.
Confirmation raises evidence and certainty but does not clear `unstable`, and
further corrections retain that history. Deferral hides all flags until its
expiry, then `unstable` returns if the history still qualifies. There is no
acknowledge/reset action: it clears only when the qualifying history no longer
exists (for example after hard deletion for an independent privacy need).
Do not delete history merely to silence the signal.
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessLimited data