agent memory agents

Bitterbot-AI/bitterbot-desktop

Agent

How to author and register a new pre-action interceptor (PLAN-20).

Bitterbot-AI/bitterbot-desktop

Agent

Operator runbook for pre-action interceptors (PLAN-20).

Bitterbot-AI/bitterbot-desktop

Agent

Executable skill interceptors turn passive markdown skills into deterministic behavioral guardrails. When the agent proposes a tool call, registered interceptors inspect the action, read the agent's current state (hormonal, GCCRF, channel, recent turns), and may modify, inject context into, require a prerequisite for…

Prismer-AI/PrismerCloud

Agent

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

Prismer-AI/PrismerCloud

Agent

Compare two outputs WITHOUT knowing which skill produced them.

Prismer-AI/PrismerCloud

Agent

Evaluate expectations against an execution transcript and outputs.

alibaba/anolisa

Agent

generate a diary for user.

sachitrafa/YourMemory

Agent

Writes and edits code. Stores strategies and implementation decisions.

sachitrafa/YourMemory

Agent

Researches APIs, docs, and external services. Stores failures and facts.

sachitrafa/YourMemory

Agent

Reviews code and stores findings privately. Does not share with other agents.

qualixar/superlocalmemory

Agent

Advises on scope, roles, compliance, and GDPR use in SuperLocalMemory. Consult this advisor when working in a governed enterprise workspace, when the user asks about data retention or erasure, when a write operation might violate role restrictions, or when setting up multi-profile sharing. Never bypasses governance…

qualixar/superlocalmemory

Agent

Runs a task as a bounded loop backed by SuperLocalMemory: iterate until an INDEPENDENT gate passes — never the agent's own claim. Delegate here when a task has a checkable acceptance condition (a test suite, a JSON schema, a linter, a reconciliation rule, a security scan) and you want gate-verified completion with an…

qualixar/superlocalmemory

Agent

Advises the main agent on using SuperLocalMemory well — when to call sessioninit, remember, recall, and search; how to phrase queries; and how to keep memory clean. Delegate here for any "should I save/recall this?" decision or when memory results look wrong.

radimsem/remindb

Agent Claude Code

Use when reviewing Go code changes in remindb (modified or staged files in pkg/, cmd/, internal/, or any .go file in the diff) for adherence to the project's .claude/rules/go-concise.md. Catches project-specific style violations that generic Go reviewers miss — empty-struct-with-methods pattern, "failed to :" error…

radimsem/remindb

Agent Claude Code

Use when reviewing changes to remindb's public MCP surface — anything in pkg/mcp/, pkg/mcp/tools/, or pkg/mcp/server.go, especially new/renamed/removed Memory tools, changes to handler signatures, return shapes, locking decisions, or defer d.logCall(...) attrs. Validates against .claude/rules/mcp-tool-conventions.md…

radimsem/remindb

Agent Claude Code

Use when reviewing changes to remindb's SQL migrations — any new file under migrations/ matching 000N.sql, any edit to an already-committed migration file, or any change to pkg/store/queries.go that adds queries against columns/tables created by recent migrations. Checks IF NOT EXISTS coverage, append-only discipline…

Necmttn/ax

Agent

Reviews ax SurrealDB schema + ingest-stage changes for the registration gotchas that fail CI.

Necmttn/ax

Agent

Reviews one prior session through ax's normalized cross-harness Turn view and emits a structured retro (tried · worked · failed · next) plus optional proposals. Dispatched by the /retro skill from a .ax/tasks/retro/ .md brief. Runs ax retro emit and, when patterns repeat, ax improve recommend. Never edits source code.

nablo-io/lerim

Agent

The context curator is the cold path. It keeps existing records compact, non-duplicative, and current.

nablo-io/lerim

Agent

The context graph agent runs after curated records are available. It builds a sparse graph of useful relationships between decisions, constraints, facts, preferences, references, evidence, and handoffs.

nablo-io/lerim

Agent

Trace ingestion is the hot path. It turns one indexed source session into a small episode record plus zero or more durable context records.

laborany/laborany

Agent

You are a benchmark analysis agent. Your job is to analyze aggregate benchmark results and surface hidden patterns, regressions, and improvement opportunities.

laborany/laborany

Agent

You are a blind comparison agent. Your job is to compare two outputs (A and B) against a rubric and determine which is better, without knowing which version produced which output.

laborany/laborany

Agent

You are an assertion grading agent. Your job is to evaluate whether assertions about a skill's output are satisfied, verify factual claims, and critique the quality of the evaluation itself.